chris/fastbook
1
0
Fork 0
mirror of https://github.com/fastai/fastbook.git synced 2025-04-05 02:10:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

remove idx_ and path_ extraneous keys in the JSON

Browse Source
This commit is contained in:
gunchu 2023-03-29 21:01:35 -07:00
parent 20a4ada9cb
commit e17eb8e4c8
24 changed files with 30 additions and 1405 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.vscode/settings.json vendored Normal file
View File

@ -0,0 +1,3 @@
{
"python.formatting.provider": "black"
}

60
clean/01_intro.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -26,7 +24,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Your Deep Learning Journey" "# Your Deep Learning Journey"
@ -34,7 +31,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Deep Learning Is for Everyone" "## Deep Learning Is for Everyone"
@ -42,7 +38,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 9,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Neural Networks: A Brief History" "## Neural Networks: A Brief History"
@ -50,7 +45,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 15,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Who We Are" "## Who We Are"
@ -58,7 +52,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 22,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## How to Learn Deep Learning" "## How to Learn Deep Learning"
@ -66,7 +59,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 26,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Your Projects and Your Mindset" "### Your Projects and Your Mindset"
@ -74,7 +66,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 31,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## The Software: PyTorch, fastai, and Jupyter" "## The Software: PyTorch, fastai, and Jupyter"
@ -82,7 +73,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 37,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Your First Model" "## Your First Model"
@ -90,7 +80,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 40,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Getting a GPU Deep Learning Server" "### Getting a GPU Deep Learning Server"
@ -98,7 +87,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 47,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Running Your First Notebook" "### Running Your First Notebook"
@ -107,7 +95,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 54,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -126,7 +113,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 57,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Sidebar: This Book Was Written in Jupyter Notebooks" "### Sidebar: This Book Was Written in Jupyter Notebooks"
@ -135,7 +121,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 60,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -145,7 +130,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 62,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -155,7 +139,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 63,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### End sidebar" "### End sidebar"
@ -164,7 +147,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 65,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -175,7 +157,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 68,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -187,7 +168,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 69,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -199,7 +179,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 71,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### What Is Machine Learning?" "### What Is Machine Learning?"
@ -208,7 +187,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 73,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -219,7 +197,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 79,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -230,7 +207,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 81,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -243,7 +219,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 83,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -253,7 +228,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 86,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### What Is a Neural Network?" "### What Is a Neural Network?"
@ -261,7 +235,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 90,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### A Bit of Deep Learning Jargon" "### A Bit of Deep Learning Jargon"
@ -270,7 +243,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 92,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -282,7 +254,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 93,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Limitations Inherent To Machine Learning\n", "### Limitations Inherent To Machine Learning\n",
@ -301,7 +272,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 96,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### How Our Image Recognizer Works" "### How Our Image Recognizer Works"
@ -309,7 +279,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 115,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### What Our Image Recognizer Learned" "### What Our Image Recognizer Learned"
@ -317,7 +286,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 125,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Image Recognizers Can Tackle Non-Image Tasks" "### Image Recognizers Can Tackle Non-Image Tasks"
@ -325,7 +293,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 137,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Jargon Recap" "### Jargon Recap"
@ -333,7 +300,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 140,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Deep Learning Is Not Just for Image Classification" "## Deep Learning Is Not Just for Image Classification"
@ -342,7 +308,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 142,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -360,7 +325,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 144,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -370,7 +334,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 146,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -383,7 +346,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 147,
"metadata": {}, "metadata": {},
"source": [ "source": [
"If you hit a \"CUDA out of memory error\" after running this cell, click on the menu Kernel, then restart. Instead of executing the cell above, copy and paste the following code in it:\n", "If you hit a \"CUDA out of memory error\" after running this cell, click on the menu Kernel, then restart. Instead of executing the cell above, copy and paste the following code in it:\n",
@ -402,7 +364,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 149,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -411,7 +372,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 151,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Sidebar: The Order Matters" "### Sidebar: The Order Matters"
@ -419,7 +379,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 153,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### End sidebar" "### End sidebar"
@ -428,7 +387,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 158,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -447,7 +405,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 160,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -457,7 +414,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 163,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -471,7 +427,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 165,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -480,7 +435,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 166,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Sidebar: Datasets: Food for Models" "### Sidebar: Datasets: Food for Models"
@ -488,7 +442,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 168,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### End sidebar" "### End sidebar"
@ -496,7 +449,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 170,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Validation Sets and Test Sets" "## Validation Sets and Test Sets"
@ -504,7 +456,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 173,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Use Judgment in Defining Test Sets" "### Use Judgment in Defining Test Sets"
@ -512,7 +463,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 185,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## A _Choose Your Own Adventure_ moment" "## A _Choose Your Own Adventure_ moment"
@ -520,7 +470,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 187,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -528,7 +477,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 188,
"metadata": {}, "metadata": {},
"source": [ "source": [
"It can be hard to know in pages and pages of prose what the key things are that you really need to focus on and remember. So, we've prepared a list of questions and suggested steps to complete at the end of each chapter. All the answers are in the text of the chapter, so if you're not sure about anything here, reread that part of the text and make sure you understand it. Answers to all these questions are also available on the [book's website](https://book.fast.ai). You can also visit [the forums](https://forums.fast.ai) if you get stuck to get help from other folks studying this material.\n", "It can be hard to know in pages and pages of prose what the key things are that you really need to focus on and remember. So, we've prepared a list of questions and suggested steps to complete at the end of each chapter. All the answers are in the text of the chapter, so if you're not sure about anything here, reread that part of the text and make sure you understand it. Answers to all these questions are also available on the [book's website](https://book.fast.ai). You can also visit [the forums](https://forums.fast.ai) if you get stuck to get help from other folks studying this material.\n",
@ -538,7 +486,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 189,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Do you need these for deep learning?\n", "1. Do you need these for deep learning?\n",
@ -584,7 +531,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 190,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -592,7 +538,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 191,
"metadata": {}, "metadata": {},
"source": [ "source": [
"Each chapter also has a \"Further Research\" section that poses questions that aren't fully answered in the text, or gives more advanced assignments. Answers to these questions aren't on the book's website; you'll need to do your own research!" "Each chapter also has a \"Further Research\" section that poses questions that aren't fully answered in the text, or gives more advanced assignments. Answers to these questions aren't on the book's website; you'll need to do your own research!"
@ -600,7 +545,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 192,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Why is a GPU useful for deep learning? How is a CPU different, and why is it less effective for deep learning?\n", "1. Why is a GPU useful for deep learning? How is a CPU different, and why is it less effective for deep learning?\n",
@ -610,7 +554,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 193,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -627,6 +570,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 4, "nbformat_minor": 4
"path_": "01_intro.ipynb"
} }

76
clean/02_production.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -27,7 +25,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# From Model to Production" "# From Model to Production"
@ -35,7 +32,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## The Practice of Deep Learning" "## The Practice of Deep Learning"
@ -43,7 +39,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 7,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Starting Your Project" "### Starting Your Project"
@ -51,7 +46,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 11,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### The State of Deep Learning" "### The State of Deep Learning"
@ -59,7 +53,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 13,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Computer vision" "#### Computer vision"
@ -67,7 +60,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 15,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Text (natural language processing)" "#### Text (natural language processing)"
@ -75,7 +67,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 17,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Combining text and images" "#### Combining text and images"
@ -83,7 +74,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 19,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Tabular data" "#### Tabular data"
@ -91,7 +81,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 21,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Recommendation systems" "#### Recommendation systems"
@ -99,7 +88,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 24,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Other data types" "#### Other data types"
@ -107,7 +95,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 26,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### The Drivetrain Approach" "### The Drivetrain Approach"
@ -115,7 +102,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 32,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Gathering Data" "## Gathering Data"
@ -123,7 +109,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 36,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# clean\n", "# clean\n",
@ -133,7 +118,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 37,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -143,7 +127,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 39,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -153,7 +136,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 40,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -165,7 +147,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 42,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -176,7 +157,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 43,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -187,7 +167,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 44,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -198,7 +177,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 46,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -209,7 +187,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 47,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -225,7 +202,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 49,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -236,7 +212,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 52,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -247,7 +222,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 54,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -256,7 +230,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 55,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Sidebar: Getting Help in Jupyter Notebooks" "### Sidebar: Getting Help in Jupyter Notebooks"
@ -264,7 +237,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 57,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### End sidebar" "### End sidebar"
@ -272,7 +244,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 62,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## From Data to DataLoaders" "## From Data to DataLoaders"
@ -281,7 +252,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 66,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -296,7 +266,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 69,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -306,7 +275,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 71,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -316,7 +284,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 73,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -328,7 +295,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 74,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -340,7 +306,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 76,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -351,7 +316,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 78,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Data Augmentation" "### Data Augmentation"
@ -360,7 +324,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 80,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -371,7 +334,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 82,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Training Your Model, and Using It to Clean Your Data" "## Training Your Model, and Using It to Clean Your Data"
@ -380,7 +342,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 84,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -393,7 +354,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 86,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -404,7 +364,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 88,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -415,7 +374,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 90,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -425,7 +383,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 92,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -436,7 +393,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 94,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -447,7 +403,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 98,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Turning Your Model into an Online Application" "## Turning Your Model into an Online Application"
@ -455,7 +410,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 100,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Using the Model for Inference" "### Using the Model for Inference"
@ -464,7 +418,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 102,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -474,7 +427,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 104,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -485,7 +437,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 106,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -495,7 +446,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 108,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -505,7 +455,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 110,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -514,7 +463,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 113,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Creating a Notebook App from the Model" "### Creating a Notebook App from the Model"
@ -523,7 +471,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 115,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -534,7 +481,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 117,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -546,7 +492,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 118,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -556,7 +501,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 121,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -569,7 +513,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 123,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -579,7 +522,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 125,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -591,7 +533,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 127,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -602,7 +543,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 129,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -619,7 +559,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 131,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -631,7 +570,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 132,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -641,7 +579,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 135,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Turning Your Notebook into a Real App" "### Turning Your Notebook into a Real App"
@ -650,7 +587,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 136,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -661,7 +597,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 138,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Deploying your app" "### Deploying your app"
@ -669,7 +604,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 145,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## How to Avoid Disaster" "## How to Avoid Disaster"
@ -677,7 +611,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 151,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Unforeseen Consequences and Feedback Loops" "### Unforeseen Consequences and Feedback Loops"
@ -685,7 +618,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 153,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Get Writing!" "## Get Writing!"
@ -693,7 +625,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 155,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -701,7 +632,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 156,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Provide an example of where the bear classification model might work poorly in production, due to structural or style differences in the training data.\n", "1. Provide an example of where the bear classification model might work poorly in production, due to structural or style differences in the training data.\n",
@ -735,7 +665,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 157,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -743,7 +672,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 158,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Consider how the Drivetrain Approach maps to a project or problem you're interested in.\n", "1. Consider how the Drivetrain Approach maps to a project or problem you're interested in.\n",
@ -755,7 +683,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 159,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -772,6 +699,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 4, "nbformat_minor": 4
"path_": "02_production.ipynb"
} }

41
clean/03_ethics.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -15,7 +14,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 2,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Data Ethics" "# Data Ethics"
@ -23,7 +21,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Sidebar: Acknowledgement: Dr. Rachel Thomas" "### Sidebar: Acknowledgement: Dr. Rachel Thomas"
@ -31,7 +28,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### End sidebar" "### End sidebar"
@ -39,7 +35,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 9,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Key Examples for Data Ethics" "## Key Examples for Data Ethics"
@ -47,7 +42,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 11,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Bugs and Recourse: Buggy Algorithm Used for Healthcare Benefits" "### Bugs and Recourse: Buggy Algorithm Used for Healthcare Benefits"
@ -55,7 +49,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 13,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Feedback Loops: YouTube's Recommendation System" "### Feedback Loops: YouTube's Recommendation System"
@ -63,7 +56,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 15,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Bias: Professor Latanya Sweeney \"Arrested\"" "### Bias: Professor Latanya Sweeney \"Arrested\""
@ -71,7 +63,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 19,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Why Does This Matter?" "### Why Does This Matter?"
@ -79,7 +70,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 25,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Integrating Machine Learning with Product Design" "## Integrating Machine Learning with Product Design"
@ -87,7 +77,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 29,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Topics in Data Ethics" "## Topics in Data Ethics"
@ -95,7 +84,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 32,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Recourse and Accountability" "### Recourse and Accountability"
@ -103,7 +91,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 34,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Feedback Loops" "### Feedback Loops"
@ -111,7 +98,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 42,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Bias" "### Bias"
@ -119,7 +105,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 46,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Historical bias" "#### Historical bias"
@ -127,7 +112,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 62,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Measurement bias" "#### Measurement bias"
@ -135,7 +119,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 64,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Aggregation bias" "#### Aggregation bias"
@ -143,7 +126,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 66,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Representation bias" "#### Representation bias"
@ -151,7 +133,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 70,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Addressing different types of bias" "### Addressing different types of bias"
@ -159,7 +140,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 73,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Disinformation" "### Disinformation"
@ -167,7 +147,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 77,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Identifying and Addressing Ethical Issues" "## Identifying and Addressing Ethical Issues"
@ -175,7 +154,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 79,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Analyze a Project You Are Working On" "### Analyze a Project You Are Working On"
@ -183,7 +161,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 81,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Processes to Implement" "### Processes to Implement"
@ -191,7 +168,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 83,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Ethical lenses" "#### Ethical lenses"
@ -199,7 +175,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 85,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### The Power of Diversity" "### The Power of Diversity"
@ -207,7 +182,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 88,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Fairness, Accountability, and Transparency" "### Fairness, Accountability, and Transparency"
@ -215,7 +189,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 92,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Role of Policy" "## Role of Policy"
@ -223,7 +196,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 94,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### The Effectiveness of Regulation" "### The Effectiveness of Regulation"
@ -231,7 +203,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 96,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Rights and Policy" "### Rights and Policy"
@ -239,7 +210,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 98,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Cars: A Historical Precedent" "### Cars: A Historical Precedent"
@ -247,7 +217,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 100,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusion" "## Conclusion"
@ -255,7 +224,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 102,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -263,7 +231,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 103,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Does ethics provide a list of \"right answers\"?\n", "1. Does ethics provide a list of \"right answers\"?\n",
@ -288,7 +255,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 104,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research:" "### Further Research:"
@ -296,7 +262,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 105,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Read the article \"What Happens When an Algorithm Cuts Your Healthcare\". How could problems like this be avoided in the future?\n", "1. Read the article \"What Happens When an Algorithm Cuts Your Healthcare\". How could problems like this be avoided in the future?\n",
@ -311,7 +276,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 106,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Deep Learning in Practice: That's a Wrap!" "## Deep Learning in Practice: That's a Wrap!"
@ -319,7 +283,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 107,
"metadata": {}, "metadata": {},
"source": [ "source": [
"Congratulations! You've made it to the end of the first section of the book. In this section we've tried to show you what deep learning can do, and how you can use it to create real applications and products. At this point, you will get a lot more out of the book if you spend some time trying out what you've learned. Perhaps you have already been doing this as you go along—in which case, great! If not, that's no problem either... Now is a great time to start experimenting yourself.\n", "Congratulations! You've made it to the end of the first section of the book. In this section we've tried to show you what deep learning can do, and how you can use it to create real applications and products. At this point, you will get a lot more out of the book if you spend some time trying out what you've learned. Perhaps you have already been doing this as you go along—in which case, great! If not, that's no problem either... Now is a great time to start experimenting yourself.\n",
@ -340,7 +303,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 108,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -357,6 +319,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 4, "nbformat_minor": 4
"path_": "03_ethics.ipynb"
} }

171
clean/04_mnist_basics.ipynb
View File

File diff suppressed because it is too large Load Diff

76
clean/05_pet_breeds.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -26,7 +24,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Image Classification" "# Image Classification"
@ -34,7 +31,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## From Dogs and Cats to Pet Breeds" "## From Dogs and Cats to Pet Breeds"
@ -43,7 +39,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -54,7 +49,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -65,7 +59,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 10,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -75,7 +68,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 12,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -85,7 +77,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 14,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -95,7 +86,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 16,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -105,7 +95,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 18,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -120,7 +109,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 20,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Presizing" "## Presizing"
@ -129,7 +117,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 24,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -158,7 +145,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 26,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Checking and Debugging a DataBlock" "### Checking and Debugging a DataBlock"
@ -167,7 +153,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 28,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -177,7 +162,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 30,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -191,7 +175,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 33,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -201,7 +184,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 35,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Cross-Entropy Loss" "## Cross-Entropy Loss"
@ -209,7 +191,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 37,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Viewing Activations and Labels" "### Viewing Activations and Labels"
@ -218,7 +199,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 39,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -228,7 +208,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 41,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -238,7 +217,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 43,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -249,7 +227,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 45,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -258,7 +235,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 47,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Softmax" "### Softmax"
@ -267,7 +243,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 49,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -277,7 +252,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 51,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -288,7 +262,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 52,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -299,7 +272,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 54,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -309,7 +281,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 56,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -319,7 +290,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 60,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -329,7 +299,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 64,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Log Likelihood" "### Log Likelihood"
@ -338,7 +307,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 66,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -348,7 +316,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 68,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -358,7 +325,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 70,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -369,7 +335,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 72,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -388,7 +353,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 75,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -398,7 +362,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 76,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -407,7 +370,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 79,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Taking the Log\n", "#### Taking the Log\n",
@ -418,7 +380,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 80,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -428,7 +389,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 83,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -438,7 +398,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 86,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -453,7 +412,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 89,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Negative Log Likelihood" "### Negative Log Likelihood"
@ -462,7 +420,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 92,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -472,7 +429,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 94,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -482,7 +438,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 96,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -492,7 +447,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 98,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -501,7 +455,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 102,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Model Interpretation" "## Model Interpretation"
@ -510,7 +463,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 104,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -521,7 +473,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 106,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -530,7 +481,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 108,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Improving Our Model" "## Improving Our Model"
@ -538,7 +488,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 110,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### The Learning Rate Finder" "### The Learning Rate Finder"
@ -547,7 +496,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 112,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -558,7 +506,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 114,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -569,7 +516,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 115,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -579,7 +525,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 117,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -589,7 +534,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 121,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Unfreezing and Transfer Learning" "### Unfreezing and Transfer Learning"
@ -598,7 +542,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 124,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -608,7 +551,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 125,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -619,7 +561,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 127,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -629,7 +570,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 129,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -639,7 +579,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 131,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -648,7 +587,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 133,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Discriminative Learning Rates" "### Discriminative Learning Rates"
@ -657,7 +595,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 137,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -670,7 +607,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 139,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -679,7 +615,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 142,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Selecting the Number of Epochs" "### Selecting the Number of Epochs"
@ -687,7 +622,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 144,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Deeper Architectures" "### Deeper Architectures"
@ -696,7 +630,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 146,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -707,7 +640,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 148,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusion" "## Conclusion"
@ -715,7 +647,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 150,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -723,7 +654,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 151,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Why do we first resize to a large size on the CPU, and then to a smaller size on the GPU?\n", "1. Why do we first resize to a large size on the CPU, and then to a smaller size on the GPU?\n",
@ -753,7 +683,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 152,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -761,7 +690,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 153,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Find the paper by Leslie Smith that introduced the learning rate finder, and read it.\n", "1. Find the paper by Leslie Smith that introduced the learning rate finder, and read it.\n",
@ -771,7 +699,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 154,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -788,6 +715,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 4, "nbformat_minor": 4
"path_": "05_pet_breeds.ipynb"
} }

75
clean/06_multicat.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -26,7 +24,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Other Computer Vision Problems" "# Other Computer Vision Problems"
@ -34,7 +31,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Multi-Label Classification" "## Multi-Label Classification"
@ -42,7 +38,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 7,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### The Data" "### The Data"
@ -51,7 +46,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -62,7 +56,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 11,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -72,7 +65,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 13,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Sidebar: Pandas and DataFrames" "### Sidebar: Pandas and DataFrames"
@ -81,7 +73,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 15,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -91,7 +82,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 16,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -104,7 +94,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 18,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -114,7 +103,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 20,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -125,7 +113,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 21,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -135,7 +122,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 23,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### End sidebar" "### End sidebar"
@ -143,7 +129,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 25,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Constructing a DataBlock" "### Constructing a DataBlock"
@ -152,7 +137,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 29,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -162,7 +146,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 31,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -172,7 +155,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 33,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -182,7 +164,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 34,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -193,7 +174,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 36,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -203,7 +183,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 37,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -215,7 +194,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 39,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -229,7 +207,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 42,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -243,7 +220,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 44,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -256,7 +232,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 48,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -267,7 +242,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 50,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -288,7 +262,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 52,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -303,7 +276,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 54,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -312,7 +284,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 57,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Binary Cross-Entropy" "### Binary Cross-Entropy"
@ -321,7 +292,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 59,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -331,7 +301,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 61,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -343,7 +312,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 63,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -353,7 +321,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 66,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -365,7 +332,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 70,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -377,7 +343,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 73,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -388,7 +353,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 75,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -399,7 +363,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 77,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -410,7 +373,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 79,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -421,7 +383,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 81,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -432,7 +393,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 83,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -442,7 +402,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 85,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -452,7 +411,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 87,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -463,7 +421,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 89,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Regression" "## Regression"
@ -471,7 +428,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 91,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Assemble the Data" "### Assemble the Data"
@ -480,7 +436,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 93,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -490,7 +445,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 94,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -501,7 +455,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 96,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -511,7 +464,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 98,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -521,7 +473,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 100,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -533,7 +484,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 102,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -544,7 +494,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 103,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -554,7 +503,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 105,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -569,7 +517,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 107,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -579,7 +526,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 109,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -595,7 +541,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 112,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -606,7 +551,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 114,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -617,7 +561,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 117,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -626,7 +569,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 120,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Training a Model" "### Training a Model"
@ -635,7 +577,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 122,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -645,7 +586,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 124,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -655,7 +595,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 126,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -665,7 +604,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 128,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -675,7 +613,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 130,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -685,7 +622,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 132,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -696,7 +632,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 134,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -706,7 +641,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 136,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -715,7 +649,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 138,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusion" "## Conclusion"
@ -723,7 +656,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 140,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -731,7 +663,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 141,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. How could multi-label classification improve the usability of the bear classifier?\n", "1. How could multi-label classification improve the usability of the bear classifier?\n",
@ -755,7 +686,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 142,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -763,7 +693,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 143,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Read a tutorial about Pandas DataFrames and experiment with a few methods that look interesting to you. See the book's website for recommended tutorials.\n", "1. Read a tutorial about Pandas DataFrames and experiment with a few methods that look interesting to you. See the book's website for recommended tutorials.\n",
@ -773,7 +702,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 144,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -790,6 +718,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 4, "nbformat_minor": 4
"path_": "06_multicat.ipynb"
} }

33
clean/07_sizing_and_tta.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -26,7 +24,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Training a State-of-the-Art Model" "# Training a State-of-the-Art Model"
@ -34,7 +31,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Imagenette" "## Imagenette"
@ -43,7 +39,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -54,7 +49,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -69,7 +63,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 11,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -80,7 +73,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 13,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Normalization" "## Normalization"
@ -89,7 +81,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 15,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -100,7 +91,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 17,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -117,7 +107,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 18,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -127,7 +116,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 19,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -138,7 +126,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 21,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -149,7 +136,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 23,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Progressive Resizing" "## Progressive Resizing"
@ -158,7 +144,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 27,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -171,7 +156,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 29,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -181,7 +165,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 31,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Test Time Augmentation" "## Test Time Augmentation"
@ -190,7 +173,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 35,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -200,7 +182,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 37,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Mixup" "## Mixup"
@ -208,7 +189,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 40,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Sidebar: Papers and Math" "### Sidebar: Papers and Math"
@ -216,7 +196,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 42,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### End sidebar" "### End sidebar"
@ -225,7 +204,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 44,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -244,7 +222,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 48,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Label Smoothing" "## Label Smoothing"
@ -252,7 +229,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 50,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Sidebar: Label Smoothing, the Paper" "### Sidebar: Label Smoothing, the Paper"
@ -260,7 +236,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 53,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### End sidebar" "### End sidebar"
@ -268,7 +243,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 55,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusion" "## Conclusion"
@ -276,7 +250,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 57,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -284,7 +257,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 58,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. What is the difference between ImageNet and Imagenette? When is it better to experiment on one versus the other?\n", "1. What is the difference between ImageNet and Imagenette? When is it better to experiment on one versus the other?\n",
@ -305,7 +277,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 59,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research\n", "### Further Research\n",
@ -319,7 +290,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 60,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -336,6 +306,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2, "nbformat_minor": 2
"path_": "07_sizing_and_tta.ipynb"
} }

72
clean/08_collab.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -26,7 +24,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Collaborative Filtering Deep Dive" "# Collaborative Filtering Deep Dive"
@ -34,7 +31,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 6,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## A First Look at the Data" "## A First Look at the Data"
@ -43,7 +39,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -55,7 +50,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 11,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -67,7 +61,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 15,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -77,7 +70,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 17,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -87,7 +79,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 19,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -97,7 +88,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 23,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -107,7 +97,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 25,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -116,7 +105,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 27,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Learning the Latent Factors" "## Learning the Latent Factors"
@ -124,7 +112,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 32,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Creating the DataLoaders" "## Creating the DataLoaders"
@ -133,7 +120,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 34,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -145,7 +131,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 36,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -156,7 +141,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 38,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -167,7 +151,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 40,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -177,7 +160,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 41,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -192,7 +174,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 43,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -202,7 +183,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 44,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -212,7 +192,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 46,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -221,7 +200,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 50,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Collaborative Filtering from Scratch" "## Collaborative Filtering from Scratch"
@ -230,7 +208,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 52,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -242,7 +219,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 54,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -253,7 +229,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 56,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -271,7 +246,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 58,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -282,7 +256,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 60,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -293,7 +266,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 62,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -303,7 +275,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 64,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -322,7 +293,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 65,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -334,7 +304,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 67,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -357,7 +326,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 69,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -368,7 +336,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 71,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Weight Decay" "### Weight Decay"
@ -377,7 +344,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 73,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -393,7 +359,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 75,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -404,7 +369,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 77,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Creating Our Own Embedding Module" "### Creating Our Own Embedding Module"
@ -413,7 +377,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 79,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -426,7 +389,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 81,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -439,7 +401,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 83,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -453,7 +414,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 84,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -463,7 +423,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 86,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -474,7 +433,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 88,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -497,7 +455,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 90,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -508,7 +465,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 92,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Interpreting Embeddings and Biases" "## Interpreting Embeddings and Biases"
@ -517,7 +473,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 94,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -529,7 +484,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 96,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -540,7 +494,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 98,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -562,7 +515,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 102,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Using fastai.collab" "### Using fastai.collab"
@ -571,7 +523,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 104,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -581,7 +532,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 105,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -591,7 +541,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 107,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -601,7 +550,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 109,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -612,7 +560,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 111,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Embedding Distance" "### Embedding Distance"
@ -621,7 +568,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 113,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -634,7 +580,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 115,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Bootstrapping a Collaborative Filtering Model" "## Bootstrapping a Collaborative Filtering Model"
@ -642,7 +587,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 119,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Deep Learning for Collaborative Filtering" "## Deep Learning for Collaborative Filtering"
@ -651,7 +595,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 121,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -662,7 +605,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 123,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -685,7 +627,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 125,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -695,7 +636,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 127,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -706,7 +646,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 129,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -717,7 +656,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 131,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -729,7 +667,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 133,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Sidebar: kwargs and Delegates" "### Sidebar: kwargs and Delegates"
@ -737,7 +674,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 135,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### End sidebar" "### End sidebar"
@ -745,7 +681,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 137,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusion" "## Conclusion"
@ -753,7 +688,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 139,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -761,7 +695,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 140,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. What problem does collaborative filtering solve?\n", "1. What problem does collaborative filtering solve?\n",
@ -799,7 +732,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 141,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research\n", "### Further Research\n",
@ -813,7 +745,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 142,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -830,6 +761,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2, "nbformat_minor": 2
"path_": "08_collab.ipynb"
} }

149
clean/09_tabular.ipynb
View File

File diff suppressed because it is too large Load Diff

73
clean/10_nlp.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -27,7 +25,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# NLP Deep Dive: RNNs" "# NLP Deep Dive: RNNs"
@ -35,7 +32,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 9,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Text Preprocessing" "## Text Preprocessing"
@ -43,7 +39,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 12,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Tokenization" "### Tokenization"
@ -51,7 +46,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 15,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Word Tokenization with fastai" "### Word Tokenization with fastai"
@ -60,7 +54,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 17,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -71,7 +64,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 19,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -81,7 +73,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 21,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -91,7 +82,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 23,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -103,7 +93,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 25,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -113,7 +102,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 27,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -124,7 +112,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 29,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -134,7 +121,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 32,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -143,7 +129,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 34,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Subword Tokenization" "### Subword Tokenization"
@ -152,7 +137,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 36,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -162,7 +146,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 38,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -175,7 +158,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 40,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -185,7 +167,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 42,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -195,7 +176,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 44,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -204,7 +184,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 47,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Numericalization with fastai" "### Numericalization with fastai"
@ -213,7 +192,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 49,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -224,7 +202,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 51,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -235,7 +212,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 53,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -247,7 +223,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 55,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -257,7 +232,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 57,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -266,7 +240,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 59,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Putting Our Texts into Batches for a Language Model" "### Putting Our Texts into Batches for a Language Model"
@ -275,7 +248,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 61,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -290,7 +262,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 63,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -303,7 +274,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 65,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -316,7 +286,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 67,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -329,7 +298,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 69,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -339,7 +307,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 71,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -349,7 +316,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 73,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -360,7 +326,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 75,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -370,7 +335,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 77,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -379,7 +343,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 79,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Training a Text Classifier" "## Training a Text Classifier"
@ -387,7 +350,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 81,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Language Model Using DataBlock" "### Language Model Using DataBlock"
@ -396,7 +358,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 83,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -411,7 +372,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 85,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -420,7 +380,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 87,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Fine-Tuning the Language Model" "### Fine-Tuning the Language Model"
@ -429,7 +388,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 89,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -441,7 +399,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 93,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -450,7 +407,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 95,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Saving and Loading Models" "### Saving and Loading Models"
@ -459,7 +415,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 97,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -469,7 +424,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 99,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -479,7 +433,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 101,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -490,7 +443,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 103,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -499,7 +451,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 106,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Text Generation" "### Text Generation"
@ -508,7 +459,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 108,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -522,7 +472,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 109,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -531,7 +480,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 111,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Creating the Classifier DataLoaders" "### Creating the Classifier DataLoaders"
@ -540,7 +488,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 113,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -555,7 +502,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 115,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -565,7 +511,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 117,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -575,7 +520,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 119,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -585,7 +529,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 121,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -596,7 +539,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 123,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -605,7 +547,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 124,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Fine-Tuning the Classifier" "### Fine-Tuning the Classifier"
@ -614,7 +555,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 126,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -624,7 +564,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 128,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -635,7 +574,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 130,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -646,7 +584,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 132,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -656,7 +593,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 134,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Disinformation and Language Models" "## Disinformation and Language Models"
@ -664,7 +600,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 142,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusion" "## Conclusion"
@ -672,7 +607,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 144,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -680,7 +614,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 145,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. What is \"self-supervised learning\"?\n", "1. What is \"self-supervised learning\"?\n",
@ -709,7 +642,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 146,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -717,7 +649,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 147,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. See what you can learn about language models and disinformation. What are the best language models today? Take a look at some of their outputs. Do you find them convincing? How could a bad actor best use such a model to create conflict and uncertainty?\n", "1. See what you can learn about language models and disinformation. What are the best language models today? Take a look at some of their outputs. Do you find them convincing? How could a bad actor best use such a model to create conflict and uncertainty?\n",
@ -727,7 +658,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 148,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -744,6 +674,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2, "nbformat_minor": 2
"path_": "10_nlp.ipynb"
} }

61
clean/11_midlevel_data.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -27,7 +25,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Data Munging with fastai's Mid-Level API" "# Data Munging with fastai's Mid-Level API"
@ -35,7 +32,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Going Deeper into fastai's Layered API" "## Going Deeper into fastai's Layered API"
@ -44,7 +40,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -56,7 +51,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -71,7 +65,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 12,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Transforms" "### Transforms"
@ -80,7 +73,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 14,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -91,7 +83,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 16,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -104,7 +95,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 18,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -117,7 +107,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 20,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -127,7 +116,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 22,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -137,7 +125,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 24,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -146,7 +133,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 25,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Writing Your Own Transform" "### Writing Your Own Transform"
@ -155,7 +141,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 27,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -167,7 +152,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 29,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -179,7 +163,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 31,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -192,7 +175,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 33,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -206,7 +188,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 35,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Pipeline" "### Pipeline"
@ -215,7 +196,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 37,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -226,7 +206,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 39,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -235,7 +214,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 41,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## TfmdLists and Datasets: Transformed Collections" "## TfmdLists and Datasets: Transformed Collections"
@ -243,7 +221,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 43,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### TfmdLists" "### TfmdLists"
@ -252,7 +229,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 45,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -262,7 +238,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 47,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -272,7 +247,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 49,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -282,7 +256,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 51,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -292,7 +265,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 53,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -305,7 +277,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 55,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -315,7 +286,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 57,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -326,7 +296,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 59,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -338,7 +307,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 61,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -348,7 +316,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 63,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Datasets" "### Datasets"
@ -357,7 +324,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 65,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -371,7 +337,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 67,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -385,7 +350,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 69,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -396,7 +360,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 71,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -406,7 +369,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 74,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -420,7 +382,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 76,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -435,7 +396,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 78,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Applying the Mid-Level Data API: SiamesePair" "## Applying the Mid-Level Data API: SiamesePair"
@ -444,7 +404,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 80,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -456,7 +415,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 82,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -476,7 +434,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 84,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -488,7 +445,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 86,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -500,7 +456,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 88,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -511,7 +466,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 90,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -522,7 +476,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 92,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -550,7 +503,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 94,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -562,7 +514,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 96,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -573,7 +524,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 98,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -583,7 +533,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 101,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusion" "## Conclusion"
@ -591,7 +540,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 103,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -599,7 +547,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 104,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Why do we say that fastai has a \"layered\" API? What does it mean?\n", "1. Why do we say that fastai has a \"layered\" API? What does it mean?\n",
@ -621,7 +568,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 105,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -629,7 +575,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 106,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Use the mid-level API to prepare the data in `DataLoaders` on your own datasets. Try this with the Pet dataset and the Adult dataset from Chapter 1.\n", "1. Use the mid-level API to prepare the data in `DataLoaders` on your own datasets. Try this with the Pet dataset and the Adult dataset from Chapter 1.\n",
@ -638,7 +583,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 107,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Understanding fastai's Applications: Wrap Up" "## Understanding fastai's Applications: Wrap Up"
@ -646,7 +590,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 108,
"metadata": {}, "metadata": {},
"source": [ "source": [
"Congratulations—you've completed all of the chapters in this book that cover the key practical parts of training models and using deep learning! You know how to use all of fastai's built-in applications, and how to customize them using the data block API and loss functions. You even know how to create a neural network from scratch, and train it! (And hopefully you now know some of the questions to ask to make sure your creations help improve society too.)\n", "Congratulations—you've completed all of the chapters in this book that cover the key practical parts of training models and using deep learning! You know how to use all of fastai's built-in applications, and how to customize them using the data block API and loss functions. You even know how to create a neural network from scratch, and train it! (And hopefully you now know some of the questions to ask to make sure your creations help improve society too.)\n",
@ -659,7 +602,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 109,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -676,6 +618,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2, "nbformat_minor": 2
"path_": "11_midlevel_data.ipynb"
} }

68
clean/12_nlp_dive.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -26,7 +24,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# A Language Model from Scratch" "# A Language Model from Scratch"
@ -34,7 +31,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## The Data" "## The Data"
@ -43,7 +39,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -54,7 +49,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 10,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -65,7 +59,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 11,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -75,7 +68,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 13,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -88,7 +80,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 15,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -99,7 +90,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 17,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -110,7 +100,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 19,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -121,7 +110,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 21,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -132,7 +120,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 23,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Our First Language Model from Scratch" "## Our First Language Model from Scratch"
@ -141,7 +128,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 25,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -151,7 +137,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 27,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -162,7 +147,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 29,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -173,7 +157,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 31,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Our Language Model in PyTorch" "### Our Language Model in PyTorch"
@ -182,7 +165,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 33,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -204,7 +186,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 41,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -216,7 +197,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 43,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -230,7 +210,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 47,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Our First Recurrent Neural Network" "### Our First Recurrent Neural Network"
@ -239,7 +218,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 49,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -260,7 +238,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 51,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -271,7 +248,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 58,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Improving the RNN" "## Improving the RNN"
@ -279,7 +255,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 60,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Maintaining the State of an RNN" "### Maintaining the State of an RNN"
@ -288,7 +263,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 62,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -313,7 +287,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 66,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -324,7 +297,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 68,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -338,7 +310,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 70,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -352,7 +323,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 72,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -363,7 +333,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 74,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Creating More Signal" "### Creating More Signal"
@ -372,7 +341,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 78,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -388,7 +356,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 80,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -398,7 +365,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 82,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -424,7 +390,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 84,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -435,7 +400,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 86,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -446,7 +410,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 88,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Multilayer RNNs" "## Multilayer RNNs"
@ -454,7 +417,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 94,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### The Model" "### The Model"
@ -463,7 +425,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 96,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -485,7 +446,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 97,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -497,7 +457,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 99,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Exploding or Disappearing Activations" "### Exploding or Disappearing Activations"
@ -505,7 +464,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 103,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## LSTM" "## LSTM"
@ -513,7 +471,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 105,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Building an LSTM from Scratch" "### Building an LSTM from Scratch"
@ -522,7 +479,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 108,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -549,7 +505,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 110,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -573,7 +528,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 112,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -583,7 +537,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 113,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -592,7 +545,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 115,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Training a Language Model Using LSTMs" "### Training a Language Model Using LSTMs"
@ -601,7 +553,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 117,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -624,7 +575,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 118,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -636,7 +586,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 120,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Regularizing an LSTM" "## Regularizing an LSTM"
@ -644,7 +593,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 122,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Dropout" "### Dropout"
@ -653,7 +601,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 126,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -667,7 +614,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 129,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Activation Regularization and Temporal Activation Regularization" "### Activation Regularization and Temporal Activation Regularization"
@ -675,7 +621,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 132,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Training a Weight-Tied Regularized LSTM" "### Training a Weight-Tied Regularized LSTM"
@ -684,7 +629,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 134,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -710,7 +654,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 136,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -722,7 +665,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 138,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -733,7 +675,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 140,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -742,7 +683,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 142,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusion" "## Conclusion"
@ -750,7 +690,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 144,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -758,7 +697,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 145,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. If the dataset for your project is so big and complicated that working with it takes a significant amount of time, what should you do?\n", "1. If the dataset for your project is so big and complicated that working with it takes a significant amount of time, what should you do?\n",
@ -804,7 +742,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 146,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -812,7 +749,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 147,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. In ` LMModel2`, why can `forward` start with `h=0`? Why don't we need to say `h=torch.zeros(...)`?\n", "1. In ` LMModel2`, why can `forward` start with `h=0`? Why don't we need to say `h=torch.zeros(...)`?\n",
@ -824,7 +760,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 148,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -841,6 +776,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2, "nbformat_minor": 2
"path_": "12_nlp_dive.ipynb"
} }

90
clean/13_convolutions.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -29,7 +27,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Convolutional Neural Networks" "# Convolutional Neural Networks"
@ -37,7 +34,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## The Magic of Convolutions" "## The Magic of Convolutions"
@ -46,7 +42,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 11,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -58,7 +53,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 13,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -68,7 +62,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 14,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -79,7 +72,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 15,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -90,7 +82,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 17,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -101,7 +92,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 18,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -111,7 +101,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 20,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -122,7 +111,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 23,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -132,7 +120,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 25,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -142,7 +129,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 27,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -153,7 +139,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 28,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -162,7 +147,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 30,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Mapping a Convolution Kernel" "### Mapping a Convolution Kernel"
@ -171,7 +155,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 34,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -181,7 +164,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 37,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -194,7 +176,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 39,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -209,7 +190,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 44,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Convolutions in PyTorch" "### Convolutions in PyTorch"
@ -218,7 +198,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 46,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -236,7 +215,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 48,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -253,7 +231,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 50,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -263,7 +240,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 52,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -273,7 +249,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 54,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -283,7 +258,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 55,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -294,7 +268,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 57,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -303,7 +276,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 60,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Strides and Padding" "### Strides and Padding"
@ -311,7 +283,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 69,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Understanding the Convolution Equations" "### Understanding the Convolution Equations"
@ -319,7 +290,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 84,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Our First Convolutional Neural Network" "## Our First Convolutional Neural Network"
@ -327,7 +297,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 86,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Creating the CNN" "### Creating the CNN"
@ -336,7 +305,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 88,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -350,7 +318,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 90,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -360,7 +327,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 92,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -374,7 +340,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 94,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -384,7 +349,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 96,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -397,7 +361,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 101,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -414,7 +377,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 104,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -424,7 +386,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 106,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -434,7 +395,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 108,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -444,7 +404,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 110,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -453,7 +412,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 112,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Understanding Convolution Arithmetic" "### Understanding Convolution Arithmetic"
@ -462,7 +420,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 114,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -473,7 +430,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 116,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -483,7 +439,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 118,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -492,7 +447,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 121,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Receptive Fields" "### Receptive Fields"
@ -500,7 +454,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 128,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### A Note About Twitter" "### A Note About Twitter"
@ -508,7 +461,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 139,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Color Images" "## Color Images"
@ -517,7 +469,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 141,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -528,7 +479,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 142,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -538,7 +488,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 144,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -549,7 +498,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 152,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Improving Training Stability" "## Improving Training Stability"
@ -558,7 +506,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 154,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -568,7 +515,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 155,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -579,7 +525,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 156,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -589,7 +534,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 158,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -608,7 +552,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 160,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -617,7 +560,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 162,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### A Simple Baseline" "### A Simple Baseline"
@ -626,7 +568,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 164,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -639,7 +580,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 166,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -657,7 +597,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 168,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -667,7 +606,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 170,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -681,7 +619,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 171,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -691,7 +628,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 173,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -701,7 +637,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 175,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -710,7 +645,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 177,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Increase Batch Size" "### Increase Batch Size"
@ -719,7 +653,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 179,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -729,7 +662,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 180,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -739,7 +671,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 182,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -748,7 +679,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 184,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### 1cycle Training" "### 1cycle Training"
@ -757,7 +687,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 186,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -771,7 +700,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 187,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -781,7 +709,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 189,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -791,7 +718,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 191,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -801,7 +727,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 193,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -811,7 +736,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 200,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -820,7 +744,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 202,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Batch Normalization" "### Batch Normalization"
@ -829,7 +752,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 206,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -843,7 +765,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 208,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -853,7 +774,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 210,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -863,7 +783,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 212,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -872,7 +791,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 214,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusions" "## Conclusions"
@ -880,7 +798,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 216,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -888,7 +805,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 217,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. What is a \"feature\"?\n", "1. What is a \"feature\"?\n",
@ -935,7 +851,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 218,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -943,7 +858,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 219,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. What features other than edge detectors have been used in computer vision (especially before deep learning became popular)?\n", "1. What features other than edge detectors have been used in computer vision (especially before deep learning became popular)?\n",
@ -954,7 +868,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 220,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -971,6 +884,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 4, "nbformat_minor": 4
"path_": "13_convolutions.ipynb"
} }

41
clean/14_resnet.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -26,7 +24,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# ResNets" "# ResNets"
@ -34,7 +31,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Going Back to Imagenette" "## Going Back to Imagenette"
@ -43,7 +39,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -61,7 +56,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 8,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -71,7 +65,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -81,7 +74,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 11,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -91,7 +83,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 13,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -111,7 +102,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 17,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -125,7 +115,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 18,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -135,7 +124,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 20,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -144,7 +132,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 22,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Building a Modern CNN: ResNet" "## Building a Modern CNN: ResNet"
@ -152,7 +139,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 24,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Skip Connections" "### Skip Connections"
@ -161,7 +147,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 31,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -177,7 +162,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 35,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -190,7 +174,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 36,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -207,7 +190,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 38,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -218,7 +200,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 39,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -228,7 +209,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 41,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -239,7 +219,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 42,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -249,7 +228,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 46,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### A State-of-the-Art ResNet" "### A State-of-the-Art ResNet"
@ -258,7 +236,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 50,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -272,7 +249,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 51,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -282,7 +258,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 55,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -308,7 +283,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 57,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -318,7 +292,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 59,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -328,7 +301,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 61,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Bottleneck Layers" "### Bottleneck Layers"
@ -337,7 +309,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 65,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -351,7 +322,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 67,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -361,7 +331,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 69,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -371,7 +340,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 70,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -381,7 +349,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 72,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusion" "## Conclusion"
@ -389,7 +356,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 74,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -397,7 +363,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 75,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. How did we get to a single vector of activations in the CNNs used for MNIST in previous chapters? Why isn't that suitable for Imagenette?\n", "1. How did we get to a single vector of activations in the CNNs used for MNIST in previous chapters? Why isn't that suitable for Imagenette?\n",
@ -426,7 +391,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 76,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -434,7 +398,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 77,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Try creating a fully convolutional net with adaptive average pooling for MNIST (note that you'll need fewer stride-2 layers). How does it compare to a network without such a pooling layer?\n", "1. Try creating a fully convolutional net with adaptive average pooling for MNIST (note that you'll need fewer stride-2 layers). How does it compare to a network without such a pooling layer?\n",
@ -446,7 +409,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 78,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -463,6 +425,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 4, "nbformat_minor": 4
"path_": "14_resnet.ipynb"
} }

30
clean/15_arch_details.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -26,7 +24,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Application Architectures Deep Dive" "# Application Architectures Deep Dive"
@ -34,7 +31,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Computer Vision" "## Computer Vision"
@ -42,7 +38,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 7,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### vision_learner" "### vision_learner"
@ -51,7 +46,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -61,7 +55,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 12,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -70,7 +63,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 17,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### unet_learner" "### unet_learner"
@ -78,7 +70,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 23,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### A Siamese Network" "### A Siamese Network"
@ -87,7 +78,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 24,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -139,7 +129,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 26,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -155,7 +144,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 28,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -165,7 +153,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 30,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -175,7 +162,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 32,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -185,7 +171,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 34,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -196,7 +181,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 36,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -207,7 +191,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 38,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -219,7 +202,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 40,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -229,7 +211,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 42,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -239,7 +220,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 45,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Natural Language Processing" "## Natural Language Processing"
@ -247,7 +227,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 49,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Tabular" "## Tabular"
@ -255,7 +234,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 52,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Wrapping Up Architectures" "## Wrapping Up Architectures"
@ -263,7 +241,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 56,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -271,7 +248,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 57,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. What is the \"head\" of a neural net?\n", "1. What is the \"head\" of a neural net?\n",
@ -296,7 +272,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 58,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -304,7 +279,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 59,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Write your own custom head and try training the pet recognizer with it. See if you can get a better result than fastai's default.\n", "1. Write your own custom head and try training the pet recognizer with it. See if you can get a better result than fastai's default.\n",
@ -317,7 +291,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 60,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -334,6 +307,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2, "nbformat_minor": 2
"path_": "15_arch_details.ipynb"
} }

46
clean/16_accel_sgd.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -26,7 +24,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# The Training Process" "# The Training Process"
@ -34,7 +31,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Establishing a Baseline" "## Establishing a Baseline"
@ -43,7 +39,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -61,7 +56,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 8,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -71,7 +65,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 10,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -83,7 +76,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 12,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -94,7 +86,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 14,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -104,7 +95,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 16,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -114,7 +104,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 18,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -123,7 +112,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 20,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## A Generic Optimizer" "## A Generic Optimizer"
@ -132,7 +120,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 23,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -142,7 +129,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 25,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -152,7 +138,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 27,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -162,7 +147,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 29,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Momentum" "## Momentum"
@ -171,7 +155,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 31,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -191,7 +174,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 33,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -215,7 +197,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 36,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -227,7 +208,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 38,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -237,7 +217,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 39,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -247,7 +226,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 41,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -258,7 +236,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 42,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -267,7 +244,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 44,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## RMSProp" "## RMSProp"
@ -276,7 +252,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 47,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -288,7 +263,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 49,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -303,7 +277,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 51,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -313,7 +286,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 53,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Adam" "## Adam"
@ -321,7 +293,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 55,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Decoupled Weight Decay" "## Decoupled Weight Decay"
@ -329,7 +300,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 57,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Callbacks" "## Callbacks"
@ -337,7 +307,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 66,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Creating a Callback" "### Creating a Callback"
@ -346,7 +315,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 69,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -358,7 +326,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 71,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -382,7 +349,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 76,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Callback Ordering and Exceptions" "### Callback Ordering and Exceptions"
@ -391,7 +357,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 78,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -404,7 +369,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 82,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusion" "## Conclusion"
@ -412,7 +376,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 84,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -420,7 +383,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 85,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. What is the equation for a step of SGD, in math or code (as you prefer)?\n", "1. What is the equation for a step of SGD, in math or code (as you prefer)?\n",
@ -454,7 +416,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 86,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -462,7 +423,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 87,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Look up the \"Rectified Adam\" paper, implement it using the general optimizer framework, and try it out. Search for other recent optimizers that work well in practice, and pick one to implement.\n", "1. Look up the \"Rectified Adam\" paper, implement it using the general optimizer framework, and try it out. Search for other recent optimizers that work well in practice, and pick one to implement.\n",
@ -473,7 +433,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 88,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Foundations of Deep Learning: Wrap up" "## Foundations of Deep Learning: Wrap up"
@ -481,7 +440,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 89,
"metadata": {}, "metadata": {},
"source": [ "source": [
"Congratulations, you have made it to the end of the \"foundations of deep learning\" section of the book! You now understand how all of fastai's applications and most important architectures are built, and the recommended ways to train them—and you have all the information you need to build these from scratch. While you probably won't need to create your own training loop, or batchnorm layer, for instance, knowing what is going on behind the scenes is very helpful for debugging, profiling, and deploying your solutions.\n", "Congratulations, you have made it to the end of the \"foundations of deep learning\" section of the book! You now understand how all of fastai's applications and most important architectures are built, and the recommended ways to train them—and you have all the information you need to build these from scratch. While you probably won't need to create your own training loop, or batchnorm layer, for instance, knowing what is going on behind the scenes is very helpful for debugging, profiling, and deploying your solutions.\n",
@ -494,7 +452,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 90,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -511,6 +468,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2, "nbformat_minor": 2
"path_": "16_accel_sgd.ipynb"
} }

105
clean/17_foundations.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -15,7 +14,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 2,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# A Neural Net from the Foundations" "# A Neural Net from the Foundations"
@ -23,7 +21,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 4,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Building a Neural Net Layer from Scratch" "## Building a Neural Net Layer from Scratch"
@ -31,7 +28,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 6,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Modeling a Neuron" "### Modeling a Neuron"
@ -39,7 +35,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 9,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Matrix Multiplication from Scratch" "### Matrix Multiplication from Scratch"
@ -48,7 +43,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 11,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -59,7 +53,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 13,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -77,7 +70,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 15,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -88,7 +80,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 17,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -98,7 +89,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 19,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -107,7 +97,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 21,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Elementwise Arithmetic" "### Elementwise Arithmetic"
@ -116,7 +105,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 23,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -128,7 +116,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 25,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -138,7 +125,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 27,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -148,7 +134,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 29,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -158,7 +143,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 31,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -169,7 +153,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 33,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -180,7 +163,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 35,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -197,7 +179,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 36,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -206,7 +187,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 38,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Broadcasting" "### Broadcasting"
@ -214,7 +194,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 40,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Broadcasting with a scalar" "#### Broadcasting with a scalar"
@ -223,7 +202,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 42,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -234,7 +212,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 44,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -244,7 +221,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 46,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Broadcasting a vector to a matrix" "#### Broadcasting a vector to a matrix"
@ -253,7 +229,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 48,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -265,7 +240,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 49,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -275,7 +249,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 51,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -285,7 +258,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 53,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -296,7 +268,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 55,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -306,7 +277,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 57,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -316,7 +286,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 59,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -328,7 +297,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 61,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -340,7 +308,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 63,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -353,7 +320,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 65,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -363,7 +329,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 67,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -374,7 +339,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 69,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -384,7 +348,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 71,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -395,7 +358,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 73,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -405,7 +367,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 75,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -415,7 +376,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 77,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -433,7 +393,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 78,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -442,7 +401,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 80,
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Broadcasting rules" "#### Broadcasting rules"
@ -450,7 +408,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 83,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Einstein Summation" "### Einstein Summation"
@ -459,7 +416,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 85,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -469,7 +425,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 87,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -478,7 +433,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 90,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## The Forward and Backward Passes" "## The Forward and Backward Passes"
@ -486,7 +440,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 92,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Defining and Initializing a Layer" "### Defining and Initializing a Layer"
@ -495,7 +448,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 94,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -505,7 +457,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 96,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -516,7 +467,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 98,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -529,7 +479,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 100,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -540,7 +489,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 102,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -550,7 +498,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 104,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -562,7 +509,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 106,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -574,7 +520,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 108,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -586,7 +531,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 110,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -596,7 +540,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 112,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -607,7 +550,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 114,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -621,7 +563,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 116,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -632,7 +573,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 118,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -642,7 +582,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 120,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -653,7 +592,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 122,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -665,7 +603,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 124,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -677,7 +614,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 126,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -688,7 +624,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 127,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -701,7 +636,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 129,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -713,7 +647,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 131,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -727,7 +660,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 133,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -738,7 +670,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 135,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -748,7 +679,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 137,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -757,7 +687,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 139,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Gradients and the Backward Pass" "### Gradients and the Backward Pass"
@ -766,7 +695,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 143,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -778,7 +706,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 145,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -790,7 +717,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 147,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -803,7 +729,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 149,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Sidebar: SymPy" "### Sidebar: SymPy"
@ -812,7 +737,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 153,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -823,7 +747,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 155,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### End sidebar" "### End sidebar"
@ -832,7 +755,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 157,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -853,7 +775,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 160,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Refactoring the Model" "### Refactoring the Model"
@ -862,7 +783,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 162,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -878,7 +798,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 164,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -899,7 +818,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 165,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -918,7 +836,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 167,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -939,7 +856,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 169,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -949,7 +865,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 171,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -959,7 +874,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 173,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -968,7 +882,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 174,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Going to PyTorch" "### Going to PyTorch"
@ -977,7 +890,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 176,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -995,7 +907,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 178,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1007,7 +918,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 179,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1025,7 +935,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 180,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1038,7 +947,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 182,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1060,7 +968,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 184,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1078,7 +985,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 186,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1090,7 +996,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 188,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1107,7 +1012,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 190,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1122,7 +1026,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 192,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusion" "## Conclusion"
@ -1130,7 +1033,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 194,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -1138,7 +1040,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 195,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Write the Python code to implement a single neuron.\n", "1. Write the Python code to implement a single neuron.\n",
@ -1185,7 +1086,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 196,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -1193,7 +1093,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 197,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Implement ReLU as a `torch.autograd.Function` and train a model with it.\n", "1. Implement ReLU as a `torch.autograd.Function` and train a model with it.\n",
@ -1205,7 +1104,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 198,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -1222,6 +1120,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2, "nbformat_minor": 2
"path_": "17_foundations.ipynb"
} }

35
clean/18_CAM.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -26,7 +24,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# CNN Interpretation with CAM" "# CNN Interpretation with CAM"
@ -34,7 +31,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## CAM and Hooks" "## CAM and Hooks"
@ -43,7 +39,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -59,7 +54,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -70,7 +64,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 11,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -81,7 +74,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 13,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -92,7 +84,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 15,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -102,7 +93,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 17,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -112,7 +102,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 19,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -122,7 +111,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 21,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -132,7 +120,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 24,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -142,7 +129,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 25,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -153,7 +139,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 27,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -167,7 +152,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 29,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -177,7 +161,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 31,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -192,7 +175,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 33,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -203,7 +185,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 36,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Gradient CAM" "## Gradient CAM"
@ -212,7 +193,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 38,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -227,7 +207,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 40,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -243,7 +222,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 42,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -254,7 +232,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 43,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -267,7 +244,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 45,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -282,7 +258,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 46,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -293,7 +268,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 48,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -305,7 +279,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 49,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusion" "## Conclusion"
@ -313,7 +286,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 51,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -321,7 +293,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 52,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. What is a \"hook\" in PyTorch?\n", "1. What is a \"hook\" in PyTorch?\n",
@ -341,7 +312,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 53,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -349,7 +319,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 54,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Try removing `keepdim` and see what happens. Look up this parameter in the PyTorch docs. Why do we need it in this notebook?\n", "1. Try removing `keepdim` and see what happens. Look up this parameter in the PyTorch docs. Why do we need it in this notebook?\n",
@ -359,7 +328,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 55,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -376,6 +344,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2, "nbformat_minor": 2
"path_": "18_CAM.ipynb"
} }

79
clean/19_learner.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -26,7 +24,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 2,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# A fastai Learner from Scratch" "# A fastai Learner from Scratch"
@ -34,7 +31,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Data" "## Data"
@ -43,7 +39,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -53,7 +48,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -64,7 +58,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 11,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -76,7 +69,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 13,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -87,7 +79,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 14,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -98,7 +89,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 16,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -108,7 +98,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 18,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -117,7 +106,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 20,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Dataset" "### Dataset"
@ -126,7 +114,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 22,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -142,7 +129,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 24,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -154,7 +140,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 26,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -166,7 +151,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 27,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -176,7 +160,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 29,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -188,7 +171,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 31,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -199,7 +181,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 33,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -220,7 +201,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 35,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -234,7 +214,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 37,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -245,7 +224,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 39,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -260,7 +238,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 41,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -271,7 +248,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 42,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -281,7 +257,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 45,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Module and Parameter" "## Module and Parameter"
@ -290,7 +265,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 47,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -302,7 +276,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 49,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -312,7 +285,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 51,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -350,7 +322,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 53,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -372,7 +343,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 55,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -383,7 +353,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 57,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -395,7 +364,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 59,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -412,7 +380,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 61,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -424,7 +391,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 63,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -437,7 +403,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 65,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -448,7 +413,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 67,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -458,7 +422,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 69,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Simple CNN" "### Simple CNN"
@ -467,7 +430,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 71,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -485,7 +447,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 75,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -496,7 +457,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 77,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -514,7 +474,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 79,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -525,7 +484,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 81,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -538,7 +496,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 83,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Loss" "## Loss"
@ -547,7 +504,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 85,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -557,7 +513,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 87,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -569,7 +524,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 89,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -580,7 +534,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 91,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -591,7 +544,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 93,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -603,7 +555,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 95,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -617,7 +568,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 97,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -627,7 +577,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 99,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -637,7 +586,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 101,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -646,7 +594,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 103,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Learner" "## Learner"
@ -655,7 +602,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 105,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -670,7 +616,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 107,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -683,7 +628,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 109,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -727,7 +671,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 111,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Callbacks" "### Callbacks"
@ -736,7 +679,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 113,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -746,7 +688,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 116,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -761,7 +702,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 118,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -785,7 +725,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 120,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -796,7 +735,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 122,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Scheduling the Learning Rate" "### Scheduling the Learning Rate"
@ -805,7 +743,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 124,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -828,7 +765,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 126,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -840,7 +776,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 128,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -851,7 +786,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 130,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -879,7 +813,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 132,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -890,7 +823,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 134,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -900,7 +832,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 136,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -909,7 +840,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 137,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Conclusion" "## Conclusion"
@ -917,7 +847,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 139,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Questionnaire" "## Questionnaire"
@ -925,7 +854,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 140,
"metadata": {}, "metadata": {},
"source": [ "source": [
"> tip: Experiments: For the questions here that ask you to explain what some function or class is, you should also complete your own code experiments." "> tip: Experiments: For the questions here that ask you to explain what some function or class is, you should also complete your own code experiments."
@ -933,7 +861,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 141,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. What is `glob`?\n", "1. What is `glob`?\n",
@ -974,7 +901,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 142,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Further Research" "### Further Research"
@ -982,7 +908,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 143,
"metadata": {}, "metadata": {},
"source": [ "source": [
"1. Write `resnet18` from scratch (refer to <<chapter_resnet>> as needed), and train it with the `Learner` in this chapter.\n", "1. Write `resnet18` from scratch (refer to <<chapter_resnet>> as needed), and train it with the `Learner` in this chapter.\n",
@ -999,7 +924,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 144,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -1016,6 +940,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2, "nbformat_minor": 2
"path_": "19_learner.ipynb"
} }

6
clean/20_conclusion.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -15,7 +14,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 2,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Concluding Thoughts" "# Concluding Thoughts"
@ -24,7 +22,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 6,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -41,6 +38,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 4, "nbformat_minor": 4
"path_": "20_conclusion.ipynb"
} }

11
clean/app_blog.ipynb
View File

@ -2,7 +2,6 @@
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 1,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Creating a Blog" "# Creating a Blog"
@ -10,7 +9,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Blogging with GitHub Pages" "## Blogging with GitHub Pages"
@ -18,7 +16,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Creating the Repository" "### Creating the Repository"
@ -26,7 +23,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 7,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Setting Up Your Home Page" "### Setting Up Your Home Page"
@ -34,7 +30,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 11,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Creating Posts" "### Creating Posts"
@ -42,7 +37,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 17,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Synchronizing GitHub and Your Computer" "### Synchronizing GitHub and Your Computer"
@ -50,7 +44,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 21,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Jupyter for Blogging" "## Jupyter for Blogging"
@ -59,7 +52,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 23,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []
@ -76,6 +68,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2, "nbformat_minor": 2
"path_": "app_blog.ipynb"
} }

29
clean/app_jupyter.ipynb
View File

@ -3,7 +3,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 0,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +15,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -25,7 +23,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 3,
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Appendix: Jupyter Notebook 101" "# Appendix: Jupyter Notebook 101"
@ -33,7 +30,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 5,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Introduction" "## Introduction"
@ -42,7 +38,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -51,7 +46,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 9,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Writing" "## Writing"
@ -60,7 +54,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 13,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -69,7 +62,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 14,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Modes" "## Modes"
@ -77,7 +69,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 16,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Other Important Considerations" "## Other Important Considerations"
@ -85,7 +76,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 19,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Markdown Formatting\n" "## Markdown Formatting\n"
@ -93,7 +83,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 20,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Italics, Bold, Strikethrough, Inline, Blockquotes and Links" "### Italics, Bold, Strikethrough, Inline, Blockquotes and Links"
@ -101,7 +90,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 22,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Headings" "### Headings"
@ -109,7 +97,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 24,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Lists" "### Lists"
@ -117,7 +104,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 26,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Code Capabilities" "## Code Capabilities"
@ -126,7 +112,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 28,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -138,7 +123,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 29,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -148,7 +132,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 30,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -162,7 +145,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 31,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -173,7 +155,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 33,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -182,7 +163,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 34,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Running the App Locally" "## Running the App Locally"
@ -190,7 +170,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 36,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Creating a Notebook" "## Creating a Notebook"
@ -198,7 +177,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 38,
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Shortcuts and Tricks" "## Shortcuts and Tricks"
@ -206,7 +184,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 40,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Command Mode Shortcuts" "### Command Mode Shortcuts"
@ -214,7 +191,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 42,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Cell Tricks" "### Cell Tricks"
@ -222,7 +198,6 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"idx_": 44,
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Line Magics" "### Line Magics"
@ -231,7 +206,6 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"idx_": 46,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -247,6 +221,5 @@
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2, "nbformat_minor": 2
"path_": "app_jupyter.ipynb"
} }

5
tools/clean.py
View File

@ -31,6 +31,11 @@ def proc_nb(fname, dest):
nb['cells'] = [clean_tags(c) for j,c in enumerate(nb['cells']) if nb['cells'] = [clean_tags(c) for j,c in enumerate(nb['cells']) if
c['cell_type']=='code' or is_header_cell(c) or is_clean_cell(c) or j >= i] c['cell_type']=='code' or is_header_cell(c) or is_clean_cell(c) or j >= i]
clean_nb(nb, clear_all=True) clean_nb(nb, clear_all=True)
if 'path_' in nb:
del nb['path_']
for c in nb['cells']:
if 'idx_' in c:
del c['idx_']
with open(dest/fname.name, 'w') as f: nbformat.write(nb, f, version=4) with open(dest/fname.name, 'w') as f: nbformat.write(nb, f, version=4)
def proc_all(path='.', dest_path='clean'): def proc_all(path='.', dest_path='clean'):