fastbook/clean/01_intro.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#hide\n",
    "from utils import *"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Your deep learning journey"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Deep learning is for everyone"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Neural networks: a brief history"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## What you will learn"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Who we are"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## How to learn deep learning"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Your projects and your mindset"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## The software: PyTorch, fastai, and Jupyter (and why it doesn't matter)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Your first model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Getting a GPU deep learning server"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Running your first notebook"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: left;\">\n",
       "      <th>epoch</th>\n",
       "      <th>train_loss</th>\n",
       "      <th>valid_loss</th>\n",
       "      <th>error_rate</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>0.169390</td>\n",
       "      <td>0.021388</td>\n",
       "      <td>0.005413</td>\n",
       "      <td>00:14</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: left;\">\n",
       "      <th>epoch</th>\n",
       "      <th>train_loss</th>\n",
       "      <th>valid_loss</th>\n",
       "      <th>error_rate</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>0.058748</td>\n",
       "      <td>0.009240</td>\n",
       "      <td>0.002706</td>\n",
       "      <td>00:19</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# CLICK ME\n",
    "from fastai2.vision.all import *\n",
    "path = untar_data(URLs.PETS)/'images'\n",
    "\n",
    "def is_cat(x): return x[0].isupper()\n",
    "dls = ImageDataLoaders.from_name_func(\n",
    "    path, get_image_files(path), valid_pct=0.2, seed=42,\n",
    "    label_func=is_cat, item_tfms=Resize(224))\n",
    "\n",
    "learn = cnn_learner(dls, resnet34, metrics=error_rate)\n",
    "learn.fine_tune(1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Sidebar: This book was written in Jupyter Notebooks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "1+1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<PIL.Image.Image image mode=RGB size=151x192 at 0x7F67678F7E90>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "img = PILImage.create('images/chapter1_cat_example.jpg')\n",
    "img.to_thumb(192)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### End sidebar"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f78619047d7544908daa7fadd3c6f0c4",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "FileUpload(value={}, description='Upload')"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "uploader = widgets.FileUpload()\n",
    "uploader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "hide_input": true
   },
   "outputs": [],
   "source": [
    "#hide\n",
    "# For the book, we can't actually click an upload button, so we fake it\n",
    "uploader = SimpleNamespace(data = ['images/chapter1_cat_example.jpg'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Is this a cat?: True.\n",
      "Probability it's a cat: 0.999986\n"
     ]
    }
   ],
   "source": [
    "img = PILImage.create(uploader.data[0])\n",
    "is_cat,_,probs = learn.predict(img)\n",
    "print(f\"Is this a cat?: {is_cat}.\")\n",
    "print(f\"Probability it's a cat: {probs[1].item():.6f}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### What is machine learning?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "hide_input": false
   },
   "outputs": [
    {
     "data": {
      "image/svg+xml": [
       "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"no\"?>\n",
       "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
       " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
       "<!-- Generated by graphviz version 2.40.1 (20161225.0304)\n",
       " -->\n",
       "<!-- Title: G Pages: 1 -->\n",
       "<svg width=\"285pt\" height=\"58pt\"\n",
       " viewBox=\"0.00 0.00 284.59 58.00\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n",
       "<g id=\"graph0\" class=\"graph\" transform=\"scale(1 1) rotate(0) translate(4 54)\">\n",
       "<title>G</title>\n",
       "<polygon fill=\"#ffffff\" stroke=\"transparent\" points=\"-4,4 -4,-54 280.5882,-54 280.5882,4 -4,4\"/>\n",
       "<!-- program -->\n",
       "<g id=\"node1\" class=\"node\">\n",
       "<title>program</title>\n",
       "<polygon fill=\"none\" stroke=\"#000000\" points=\"172.9942,-50 104.9942,-50 100.9942,-46 100.9942,0 168.9942,0 172.9942,-4 172.9942,-50\"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"168.9942,-46 100.9942,-46 \"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"168.9942,-46 168.9942,0 \"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"168.9942,-46 172.9942,-50 \"/>\n",
       "<text text-anchor=\"middle\" x=\"136.9942\" y=\"-21.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">program</text>\n",
       "</g>\n",
       "<!-- results -->\n",
       "<g id=\"node3\" class=\"node\">\n",
       "<title>results</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"242.7912\" cy=\"-25\" rx=\"33.5952\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"242.7912\" y=\"-21.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">results</text>\n",
       "</g>\n",
       "<!-- program&#45;&gt;results -->\n",
       "<g id=\"edge2\" class=\"edge\">\n",
       "<title>program&#45;&gt;results</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M173.1077,-25C181.3637,-25 190.2284,-25 198.7746,-25\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"198.9789,-28.5001 208.9789,-25 198.9788,-21.5001 198.9789,-28.5001\"/>\n",
       "</g>\n",
       "<!-- inputs -->\n",
       "<g id=\"node2\" class=\"node\">\n",
       "<title>inputs</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"32.4971\" cy=\"-25\" rx=\"32.4942\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"32.4971\" y=\"-21.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">inputs</text>\n",
       "</g>\n",
       "<!-- inputs&#45;&gt;program -->\n",
       "<g id=\"edge1\" class=\"edge\">\n",
       "<title>inputs&#45;&gt;program</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M65.2739,-25C73.2739,-25 81.9845,-25 90.4897,-25\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"90.7006,-28.5001 100.7006,-25 90.7005,-21.5001 90.7006,-28.5001\"/>\n",
       "</g>\n",
       "</g>\n",
       "</svg>\n"
      ],
      "text/plain": [
       "<graphviz.files.Source at 0x7fb712ad6310>"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gv('''program[shape=box3d width=1 height=0.7]\n",
    "inputs->program->results''')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "hide_input": true
   },
   "outputs": [
    {
     "data": {
      "image/svg+xml": [
       "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"no\"?>\n",
       "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
       " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
       "<!-- Generated by graphviz version 2.40.1 (20161225.0304)\n",
       " -->\n",
       "<!-- Title: G Pages: 1 -->\n",
       "<svg width=\"296pt\" height=\"98pt\"\n",
       " viewBox=\"0.00 0.00 296.29 98.00\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n",
       "<g id=\"graph0\" class=\"graph\" transform=\"scale(1 1) rotate(0) translate(4 94)\">\n",
       "<title>G</title>\n",
       "<polygon fill=\"#ffffff\" stroke=\"transparent\" points=\"-4,4 -4,-94 292.2872,-94 292.2872,4 -4,4\"/>\n",
       "<!-- model -->\n",
       "<g id=\"node1\" class=\"node\">\n",
       "<title>model</title>\n",
       "<polygon fill=\"none\" stroke=\"#000000\" points=\"184.6932,-70 116.6932,-70 112.6932,-66 112.6932,-20 180.6932,-20 184.6932,-24 184.6932,-70\"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"180.6932,-66 112.6932,-66 \"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"180.6932,-66 180.6932,-20 \"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"180.6932,-66 184.6932,-70 \"/>\n",
       "<text text-anchor=\"middle\" x=\"148.6932\" y=\"-41.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">model</text>\n",
       "</g>\n",
       "<!-- results -->\n",
       "<g id=\"node3\" class=\"node\">\n",
       "<title>results</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"254.4902\" cy=\"-45\" rx=\"33.5952\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"254.4902\" y=\"-41.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">results</text>\n",
       "</g>\n",
       "<!-- model&#45;&gt;results -->\n",
       "<g id=\"edge2\" class=\"edge\">\n",
       "<title>model&#45;&gt;results</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M184.8066,-45C193.0627,-45 201.9273,-45 210.4735,-45\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"210.6779,-48.5001 220.6778,-45 210.6778,-41.5001 210.6779,-48.5001\"/>\n",
       "</g>\n",
       "<!-- inputs -->\n",
       "<g id=\"node2\" class=\"node\">\n",
       "<title>inputs</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"38.3466\" cy=\"-72\" rx=\"32.4942\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"38.3466\" y=\"-68.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">inputs</text>\n",
       "</g>\n",
       "<!-- inputs&#45;&gt;model -->\n",
       "<g id=\"edge1\" class=\"edge\">\n",
       "<title>inputs&#45;&gt;model</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M68.208,-64.6934C78.7724,-62.1085 90.9176,-59.1367 102.5174,-56.2985\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"103.6359,-59.6281 112.5174,-53.8516 101.9721,-52.8287 103.6359,-59.6281\"/>\n",
       "</g>\n",
       "<!-- weights -->\n",
       "<g id=\"node4\" class=\"node\">\n",
       "<title>weights</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"38.3466\" cy=\"-18\" rx=\"38.1938\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"38.3466\" y=\"-14.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">weights</text>\n",
       "</g>\n",
       "<!-- weights&#45;&gt;model -->\n",
       "<g id=\"edge3\" class=\"edge\">\n",
       "<title>weights&#45;&gt;model</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M72.3546,-26.3212C81.8534,-28.6454 92.3387,-31.211 102.4171,-33.677\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"101.763,-37.1201 112.3084,-36.0972 103.4268,-30.3207 101.763,-37.1201\"/>\n",
       "</g>\n",
       "</g>\n",
       "</svg>\n"
      ],
      "text/plain": [
       "<graphviz.files.Source at 0x7fb71350edd0>"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gv('''model[shape=box3d width=1 height=0.7]\n",
    "inputs->model->results; weights->model''')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "hide_input": true
   },
   "outputs": [
    {
     "data": {
      "image/svg+xml": [
       "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"no\"?>\n",
       "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
       " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
       "<!-- Generated by graphviz version 2.40.1 (20161225.0304)\n",
       " -->\n",
       "<!-- Title: G Pages: 1 -->\n",
       "<svg width=\"483pt\" height=\"98pt\"\n",
       " viewBox=\"0.00 0.00 483.08 98.00\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n",
       "<g id=\"graph0\" class=\"graph\" transform=\"scale(1 1) rotate(0) translate(4 94)\">\n",
       "<title>G</title>\n",
       "<polygon fill=\"#ffffff\" stroke=\"transparent\" points=\"-4,4 -4,-94 479.0773,-94 479.0773,4 -4,4\"/>\n",
       "<!-- model -->\n",
       "<g id=\"node1\" class=\"node\">\n",
       "<title>model</title>\n",
       "<polygon fill=\"none\" stroke=\"#000000\" points=\"185.6932,-77 117.6932,-77 113.6932,-73 113.6932,-27 181.6932,-27 185.6932,-31 185.6932,-77\"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"181.6932,-73 113.6932,-73 \"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"181.6932,-73 181.6932,-27 \"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"181.6932,-73 185.6932,-77 \"/>\n",
       "<text text-anchor=\"middle\" x=\"149.6932\" y=\"-48.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">model</text>\n",
       "</g>\n",
       "<!-- results -->\n",
       "<g id=\"node3\" class=\"node\">\n",
       "<title>results</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"292.4902\" cy=\"-52\" rx=\"33.5952\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"292.4902\" y=\"-48.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">results</text>\n",
       "</g>\n",
       "<!-- model&#45;&gt;results -->\n",
       "<g id=\"edge2\" class=\"edge\">\n",
       "<title>model&#45;&gt;results</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M185.7269,-52C204.7235,-52 228.1886,-52 248.278,-52\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"248.4342,-55.5001 258.4342,-52 248.4341,-48.5001 248.4342,-55.5001\"/>\n",
       "</g>\n",
       "<!-- inputs -->\n",
       "<g id=\"node2\" class=\"node\">\n",
       "<title>inputs</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"38.3466\" cy=\"-72\" rx=\"32.4942\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"38.3466\" y=\"-68.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">inputs</text>\n",
       "</g>\n",
       "<!-- inputs&#45;&gt;model -->\n",
       "<g id=\"edge1\" class=\"edge\">\n",
       "<title>inputs&#45;&gt;model</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M69.3628,-66.4289C79.914,-64.5337 91.9459,-62.3725 103.4279,-60.3101\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"104.102,-63.7452 113.3257,-58.5323 102.8644,-56.8554 104.102,-63.7452\"/>\n",
       "</g>\n",
       "<!-- performance -->\n",
       "<g id=\"node5\" class=\"node\">\n",
       "<title>performance</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"419.1822\" cy=\"-52\" rx=\"55.7903\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"419.1822\" y=\"-48.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">performance</text>\n",
       "</g>\n",
       "<!-- results&#45;&gt;performance -->\n",
       "<g id=\"edge4\" class=\"edge\">\n",
       "<title>results&#45;&gt;performance</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M326.4413,-52C334.7307,-52 343.8829,-52 353.1124,-52\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"353.1206,-55.5001 363.1205,-52 353.1205,-48.5001 353.1206,-55.5001\"/>\n",
       "</g>\n",
       "<!-- weights -->\n",
       "<g id=\"node4\" class=\"node\">\n",
       "<title>weights</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"38.3466\" cy=\"-18\" rx=\"38.1938\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"38.3466\" y=\"-14.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">weights</text>\n",
       "</g>\n",
       "<!-- weights&#45;&gt;model -->\n",
       "<g id=\"edge3\" class=\"edge\">\n",
       "<title>weights&#45;&gt;model</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M70.5526,-27.8342C80.9847,-31.0197 92.7624,-34.616 103.982,-38.042\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"103.064,-41.4211 113.6503,-40.9942 105.1084,-34.7263 103.064,-41.4211\"/>\n",
       "</g>\n",
       "<!-- performance&#45;&gt;weights -->\n",
       "<g id=\"edge5\" class=\"edge\">\n",
       "<title>performance&#45;&gt;weights</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M380.7799,-38.6552C364.2203,-33.4733 344.5068,-28.0582 326.2872,-25 242.9542,-11.0123 144.1752,-12.4408 86.651,-15.0281\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"86.2233,-11.5445 76.4031,-15.5212 86.5598,-18.5364 86.2233,-11.5445\"/>\n",
       "<text text-anchor=\"middle\" x=\"222.1932\" y=\"-19.8\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">update</text>\n",
       "</g>\n",
       "</g>\n",
       "</svg>\n"
      ],
      "text/plain": [
       "<graphviz.files.Source at 0x7f3e58071bd0>"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gv('''ordering=in\n",
    "model[shape=box3d width=1 height=0.7]\n",
    "inputs->model->results; weights->model; results->performance\n",
    "performance->weights[constraint=false label=update]''')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "hide_input": true
   },
   "outputs": [
    {
     "data": {
      "image/svg+xml": [
       "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"no\"?>\n",
       "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
       " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
       "<!-- Generated by graphviz version 2.40.1 (20161225.0304)\n",
       " -->\n",
       "<!-- Title: G Pages: 1 -->\n",
       "<svg width=\"285pt\" height=\"58pt\"\n",
       " viewBox=\"0.00 0.00 284.59 58.00\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n",
       "<g id=\"graph0\" class=\"graph\" transform=\"scale(1 1) rotate(0) translate(4 54)\">\n",
       "<title>G</title>\n",
       "<polygon fill=\"#ffffff\" stroke=\"transparent\" points=\"-4,4 -4,-54 280.5882,-54 280.5882,4 -4,4\"/>\n",
       "<!-- model -->\n",
       "<g id=\"node1\" class=\"node\">\n",
       "<title>model</title>\n",
       "<polygon fill=\"none\" stroke=\"#000000\" points=\"172.9942,-50 104.9942,-50 100.9942,-46 100.9942,0 168.9942,0 172.9942,-4 172.9942,-50\"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"168.9942,-46 100.9942,-46 \"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"168.9942,-46 168.9942,0 \"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"168.9942,-46 172.9942,-50 \"/>\n",
       "<text text-anchor=\"middle\" x=\"136.9942\" y=\"-21.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">model</text>\n",
       "</g>\n",
       "<!-- results -->\n",
       "<g id=\"node3\" class=\"node\">\n",
       "<title>results</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"242.7912\" cy=\"-25\" rx=\"33.5952\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"242.7912\" y=\"-21.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">results</text>\n",
       "</g>\n",
       "<!-- model&#45;&gt;results -->\n",
       "<g id=\"edge2\" class=\"edge\">\n",
       "<title>model&#45;&gt;results</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M173.1077,-25C181.3637,-25 190.2284,-25 198.7746,-25\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"198.9789,-28.5001 208.9789,-25 198.9788,-21.5001 198.9789,-28.5001\"/>\n",
       "</g>\n",
       "<!-- inputs -->\n",
       "<g id=\"node2\" class=\"node\">\n",
       "<title>inputs</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"32.4971\" cy=\"-25\" rx=\"32.4942\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"32.4971\" y=\"-21.3\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">inputs</text>\n",
       "</g>\n",
       "<!-- inputs&#45;&gt;model -->\n",
       "<g id=\"edge1\" class=\"edge\">\n",
       "<title>inputs&#45;&gt;model</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M65.2739,-25C73.2739,-25 81.9845,-25 90.4897,-25\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"90.7006,-28.5001 100.7006,-25 90.7005,-21.5001 90.7006,-28.5001\"/>\n",
       "</g>\n",
       "</g>\n",
       "</svg>\n"
      ],
      "text/plain": [
       "<graphviz.files.Source at 0x7fb712ade110>"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gv('''model[shape=box3d width=1 height=0.7]\n",
    "inputs->model->results''')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### What is a neural network?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### A bit of deep learning jargon"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "hide_input": true
   },
   "outputs": [
    {
     "data": {
      "image/svg+xml": [
       "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"no\"?>\n",
       "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
       " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
       "<!-- Generated by graphviz version 2.40.1 (20161225.0304)\n",
       " -->\n",
       "<!-- Title: G Pages: 1 -->\n",
       "<svg width=\"489pt\" height=\"134pt\"\n",
       " viewBox=\"0.00 0.00 489.18 134.20\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n",
       "<g id=\"graph0\" class=\"graph\" transform=\"scale(1 1) rotate(0) translate(4 130.2026)\">\n",
       "<title>G</title>\n",
       "<polygon fill=\"#ffffff\" stroke=\"transparent\" points=\"-4,4 -4,-130.2026 485.1822,-130.2026 485.1822,4 -4,4\"/>\n",
       "<!-- model -->\n",
       "<g id=\"node1\" class=\"node\">\n",
       "<title>model</title>\n",
       "<polygon fill=\"none\" stroke=\"#000000\" points=\"217.0911,-79.2026 141.0911,-79.2026 137.0911,-75.2026 137.0911,-29.2026 213.0911,-29.2026 217.0911,-33.2026 217.0911,-79.2026\"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"213.0911,-75.2026 137.0911,-75.2026 \"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"213.0911,-75.2026 213.0911,-29.2026 \"/>\n",
       "<polyline fill=\"none\" stroke=\"#000000\" points=\"213.0911,-75.2026 217.0911,-79.2026 \"/>\n",
       "<text text-anchor=\"middle\" x=\"177.0911\" y=\"-50.5026\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">architecture</text>\n",
       "</g>\n",
       "<!-- predictions -->\n",
       "<g id=\"node3\" class=\"node\">\n",
       "<title>predictions</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"340.1367\" cy=\"-54.2026\" rx=\"50.0912\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"340.1367\" y=\"-50.5026\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">predictions</text>\n",
       "</g>\n",
       "<!-- model&#45;&gt;predictions -->\n",
       "<g id=\"edge2\" class=\"edge\">\n",
       "<title>model&#45;&gt;predictions</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M217.3945,-54.2026C236.277,-54.2026 259.1631,-54.2026 280.0334,-54.2026\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"280.0905,-57.7027 290.0905,-54.2026 280.0905,-50.7027 280.0905,-57.7027\"/>\n",
       "</g>\n",
       "<!-- inputs -->\n",
       "<g id=\"node2\" class=\"node\">\n",
       "<title>inputs</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"50.0456\" cy=\"-74.2026\" rx=\"32.4942\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"50.0456\" y=\"-70.5026\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">inputs</text>\n",
       "</g>\n",
       "<!-- inputs&#45;&gt;model -->\n",
       "<g id=\"edge1\" class=\"edge\">\n",
       "<title>inputs&#45;&gt;model</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M81.4501,-69.2588C95.1932,-67.0953 111.6581,-64.5034 127.0224,-62.0847\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"127.5863,-65.5391 136.9204,-60.5265 126.4977,-58.6242 127.5863,-65.5391\"/>\n",
       "</g>\n",
       "<!-- loss -->\n",
       "<g id=\"node6\" class=\"node\">\n",
       "<title>loss</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"454.1822\" cy=\"-83.2026\" rx=\"27\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"454.1822\" y=\"-79.5026\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">loss</text>\n",
       "</g>\n",
       "<!-- predictions&#45;&gt;loss -->\n",
       "<g id=\"edge5\" class=\"edge\">\n",
       "<title>predictions&#45;&gt;loss</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M381.3097,-64.6723C393.5479,-67.7843 406.8441,-71.1653 418.6879,-74.177\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"418.105,-77.6401 428.6592,-76.7125 419.8302,-70.856 418.105,-77.6401\"/>\n",
       "</g>\n",
       "<!-- parameters -->\n",
       "<g id=\"node4\" class=\"node\">\n",
       "<title>parameters</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"50.0456\" cy=\"-20.2026\" rx=\"50.0912\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"50.0456\" y=\"-16.5026\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">parameters</text>\n",
       "</g>\n",
       "<!-- parameters&#45;&gt;model -->\n",
       "<g id=\"edge3\" class=\"edge\">\n",
       "<title>parameters&#45;&gt;model</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M90.2436,-30.9605C101.8295,-34.0611 114.6176,-37.4834 126.7368,-40.7268\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"126.1536,-44.1938 136.7185,-43.3981 127.9633,-37.4318 126.1536,-44.1938\"/>\n",
       "</g>\n",
       "<!-- labels -->\n",
       "<g id=\"node5\" class=\"node\">\n",
       "<title>labels</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"340.1367\" cy=\"-108.2026\" rx=\"31.3957\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"340.1367\" y=\"-104.5026\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">labels</text>\n",
       "</g>\n",
       "<!-- labels&#45;&gt;loss -->\n",
       "<g id=\"edge4\" class=\"edge\">\n",
       "<title>labels&#45;&gt;loss</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M369.5062,-101.7645C384.4486,-98.489 402.7335,-94.4808 418.483,-91.0283\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"419.3874,-94.4132 428.4059,-88.8531 417.8884,-87.5756 419.3874,-94.4132\"/>\n",
       "</g>\n",
       "<!-- loss&#45;&gt;parameters -->\n",
       "<g id=\"edge6\" class=\"edge\">\n",
       "<title>loss&#45;&gt;parameters</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M441.3968,-67.1028C429.6802,-53.7017 411.0259,-35.5188 390.1822,-27.2026 295.3447,10.6354 173.4836,.5619 104.3447,-9.9693\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"103.4538,-6.5667 94.1247,-11.5883 104.5492,-13.4805 103.4538,-6.5667\"/>\n",
       "<text text-anchor=\"middle\" x=\"253.5911\" y=\"-6.0026\" font-family=\"Times,serif\" font-size=\"14.00\" fill=\"#000000\">update</text>\n",
       "</g>\n",
       "</g>\n",
       "</svg>\n"
      ],
      "text/plain": [
       "<graphviz.files.Source at 0x7f3e2dc3ba90>"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gv('''ordering=in\n",
    "model[shape=box3d width=1 height=0.7 label=architecture]\n",
    "inputs->model->predictions; parameters->model; labels->loss; predictions->loss\n",
    "loss->parameters[constraint=false label=update]''')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Limitations inherent to machine learning\n",
    "\n",
    "From this picture we can now see some fundamental things about training a deep learning model:\n",
    "\n",
    "- A model cannot be created without data ;\n",
    "- A model can only learn to operate on the patterns seen in the input data used to train it ;\n",
    "- This learning approach only creates *predictions*, not recommended *actions* ;\n",
    "- It's not enough to just have examples of input data; we need *labels* for that data too (e.g. pictures of dogs and cats aren't enough to train a model; we need a label for each one, saying which ones are dogs, and which are cats).\n",
    "\n",
    "Generally speaking, we've seen that most organizations that think they don't have enough data, actually mean they don't have enough *labeled* data. If any organization is interested in doing something in practice with a model, then presumably they have some inputs they plan to run their model against. And presumably they've been doing that some other way for a while (e.g. manually, or with some heuristic program), so they have data from those processes! For instance, a radiology practice will almost certainly have an archive of medical scans (since they need to be able to check how their patients are progressing over time), but those scans may not have structured labels containing a list of diagnoses or interventions (since radiologists generally create free text natural language reports, not structured data). We'll be discussing labeling approaches a lot in this book, since it's such an important issue in practice.\n",
    "\n",
    "Since these kinds of machine learning models can only make *predictions* (i.e. attempt to replicate labels), this can result in a significant gap between organizational goals and model capabilities. For instance, in this book you'll learn how to create a *recommendation system* that can predict what products a user might purchase. This is often used in e-commerce, such as to customize products shown on a home page, by showing the highest-ranked items. But such a model is generally created by looking at a user and their buying history (*inputs*) and what they went on to buy or look at (*labels*), which means that the model is likely to tell you about products they already have, or already know about, rather than new products that they are most likely to be interested in hearing about. That's very different to what, say, an expert at your local bookseller might do, where they ask questions to figure out your taste, and then tell you about authors or series that you've never heard of before."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### How our image recognizer works"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### What our image recognizer learned"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Image recognizers can tackle non-image tasks"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Jargon recap"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Deep learning is not just for image classification"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: left;\">\n",
       "      <th>epoch</th>\n",
       "      <th>train_loss</th>\n",
       "      <th>valid_loss</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>2.906601</td>\n",
       "      <td>2.347491</td>\n",
       "      <td>00:02</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: left;\">\n",
       "      <th>epoch</th>\n",
       "      <th>train_loss</th>\n",
       "      <th>valid_loss</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1.988776</td>\n",
       "      <td>1.765969</td>\n",
       "      <td>00:02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>1.703356</td>\n",
       "      <td>1.265247</td>\n",
       "      <td>00:02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>1.591550</td>\n",
       "      <td>1.309860</td>\n",
       "      <td>00:02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>1.459745</td>\n",
       "      <td>1.102660</td>\n",
       "      <td>00:02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>1.324229</td>\n",
       "      <td>0.948472</td>\n",
       "      <td>00:02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5</td>\n",
       "      <td>1.205859</td>\n",
       "      <td>0.894631</td>\n",
       "      <td>00:02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6</td>\n",
       "      <td>1.102528</td>\n",
       "      <td>0.809563</td>\n",
       "      <td>00:02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7</td>\n",
       "      <td>1.020853</td>\n",
       "      <td>0.805135</td>\n",
       "      <td>00:02</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "path = untar_data(URLs.CAMVID_TINY)\n",
    "dls = SegmentationDataLoaders.from_label_func(\n",
    "    path, bs=8, fnames = get_image_files(path/\"images\"),\n",
    "    label_func = lambda o: path/'labels'/f'{o.stem}_P{o.suffix}',\n",
    "    codes = np.loadtxt(path/'codes.txt', dtype=str)\n",
    ")\n",
    "\n",
    "learn = unet_learner(dls, resnet34)\n",
    "learn.fine_tune(8)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x576 with 6 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "learn.show_results(max_n=6, figsize=(7,8))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: left;\">\n",
       "      <th>epoch</th>\n",
       "      <th>train_loss</th>\n",
       "      <th>valid_loss</th>\n",
       "      <th>accuracy</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>0.594912</td>\n",
       "      <td>0.407416</td>\n",
       "      <td>0.823640</td>\n",
       "      <td>01:35</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: left;\">\n",
       "      <th>epoch</th>\n",
       "      <th>train_loss</th>\n",
       "      <th>valid_loss</th>\n",
       "      <th>accuracy</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>0.268259</td>\n",
       "      <td>0.316242</td>\n",
       "      <td>0.876000</td>\n",
       "      <td>03:03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>0.184861</td>\n",
       "      <td>0.246242</td>\n",
       "      <td>0.898080</td>\n",
       "      <td>03:10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>0.136392</td>\n",
       "      <td>0.220086</td>\n",
       "      <td>0.918200</td>\n",
       "      <td>03:16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>0.106423</td>\n",
       "      <td>0.191092</td>\n",
       "      <td>0.931360</td>\n",
       "      <td>03:15</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from fastai2.text.all import *\n",
    "\n",
    "dls = TextDataLoaders.from_folder(untar_data(URLs.IMDB), valid='test')\n",
    "learn = text_classifier_learner(dls, AWD_LSTM, drop_mult=0.5, metrics=accuracy)\n",
    "learn.fine_tune(4, 1e-2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "('pos', tensor(1), tensor([0.0041, 0.9959]))"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "learn.predict(\"I really liked that movie!\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Sidebar: The order matter"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### End sidebar"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastai2.tabular.all import *\n",
    "path = untar_data(URLs.ADULT_SAMPLE)\n",
    "\n",
    "dls = TabularDataLoaders.from_csv(path/'adult.csv', path, y_names=\"salary\",\n",
    "    cat_names = ['workclass', 'education', 'marital-status', 'occupation',\n",
    "                 'relationship', 'race'],\n",
    "    cont_names = ['age', 'fnlwgt', 'education-num'],\n",
    "    procs = [Categorify, FillMissing, Normalize])\n",
    "\n",
    "learn = tabular_learner(dls, metrics=accuracy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: left;\">\n",
       "      <th>epoch</th>\n",
       "      <th>train_loss</th>\n",
       "      <th>valid_loss</th>\n",
       "      <th>accuracy</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>0.359960</td>\n",
       "      <td>0.357917</td>\n",
       "      <td>0.831388</td>\n",
       "      <td>00:11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>0.353458</td>\n",
       "      <td>0.349657</td>\n",
       "      <td>0.837991</td>\n",
       "      <td>00:10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>0.338368</td>\n",
       "      <td>0.346997</td>\n",
       "      <td>0.843213</td>\n",
       "      <td>00:10</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "learn.fit_one_cycle(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: left;\">\n",
       "      <th>epoch</th>\n",
       "      <th>train_loss</th>\n",
       "      <th>valid_loss</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1.554056</td>\n",
       "      <td>1.428071</td>\n",
       "      <td>00:01</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: left;\">\n",
       "      <th>epoch</th>\n",
       "      <th>train_loss</th>\n",
       "      <th>valid_loss</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1.393103</td>\n",
       "      <td>1.361342</td>\n",
       "      <td>00:01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>1.297930</td>\n",
       "      <td>1.159169</td>\n",
       "      <td>00:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>1.052705</td>\n",
       "      <td>0.827934</td>\n",
       "      <td>00:01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>0.810124</td>\n",
       "      <td>0.668735</td>\n",
       "      <td>00:01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>0.711552</td>\n",
       "      <td>0.627836</td>\n",
       "      <td>00:01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5</td>\n",
       "      <td>0.657402</td>\n",
       "      <td>0.611715</td>\n",
       "      <td>00:01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6</td>\n",
       "      <td>0.633079</td>\n",
       "      <td>0.605733</td>\n",
       "      <td>00:01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7</td>\n",
       "      <td>0.622399</td>\n",
       "      <td>0.602674</td>\n",
       "      <td>00:01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>8</td>\n",
       "      <td>0.629075</td>\n",
       "      <td>0.601671</td>\n",
       "      <td>00:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>9</td>\n",
       "      <td>0.619955</td>\n",
       "      <td>0.601550</td>\n",
       "      <td>00:01</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from fastai2.collab import *\n",
    "path = untar_data(URLs.ML_SAMPLE)\n",
    "dls = CollabDataLoaders.from_csv(path/'ratings.csv')\n",
    "learn = collab_learner(dls, y_range=(0.5,5.5))\n",
    "learn.fine_tune(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>userId</th>\n",
       "      <th>movieId</th>\n",
       "      <th>rating</th>\n",
       "      <th>rating_pred</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>157</td>\n",
       "      <td>1200</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3.558502</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>23</td>\n",
       "      <td>344</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.700709</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>19</td>\n",
       "      <td>1221</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.390801</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>430</td>\n",
       "      <td>592</td>\n",
       "      <td>3.5</td>\n",
       "      <td>3.944848</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>547</td>\n",
       "      <td>858</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.076881</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>292</td>\n",
       "      <td>39</td>\n",
       "      <td>4.5</td>\n",
       "      <td>3.753513</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>529</td>\n",
       "      <td>1265</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3.349463</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>19</td>\n",
       "      <td>231</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2.881087</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>475</td>\n",
       "      <td>4963</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.023387</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>130</td>\n",
       "      <td>260</td>\n",
       "      <td>4.5</td>\n",
       "      <td>3.979703</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "learn.show_results()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Sidebar: Datasets: food for models"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### End sidebar"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Validation sets and test sets"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Use judgment in defining test sets"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## A _Choose Your Own Adventure_ moment"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Questionnaire"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Further research"
   ]
  }
 ],
 "metadata": {
  "jupytext": {
   "split_at_heading": true
  },
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}