From 8415c675a5fb1a1a2dc98e6bf1cf9c56066a9507 Mon Sep 17 00:00:00 2001
From: ThuanNaN <duongthuan1445@gmail.com>
Date: Mon, 13 Jan 2025 11:07:02 +0700
Subject: [PATCH] add normalize bbox

---
 create_dataset.ipynb | 51 ++++++++++++++++++++++++++++++++------------
 1 file changed, 37 insertions(+), 14 deletions(-)

diff --git a/create_dataset.ipynb b/create_dataset.ipynb
index 6c6c54e..ca909ee 100644
--- a/create_dataset.ipynb
+++ b/create_dataset.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -15,7 +15,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -30,7 +30,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def normalize_bbox(bbox, width, height):\n",
+    "    \"\"\"\n",
+    "    Normalize bounding box to the range [0, 100].\n",
+    "    \"\"\"\n",
+    "    return [\n",
+    "        int((bbox[0] / width) * 100),  # x_min\n",
+    "        int((bbox[1] / height) * 100),  # y_min\n",
+    "        int((bbox[2] / width) * 100),  # x_max\n",
+    "        int((bbox[3] / height) * 100),  # y_max\n",
+    "    ]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -144,7 +162,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -153,7 +171,7 @@
        "5354"
       ]
      },
-     "execution_count": 51,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -164,7 +182,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -178,17 +196,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
     "for data in mvtech_ad_data_for_regression:\n",
-    "    data[\"image_path\"] = data[\"image_path\"].replace(\"MVTEC_det\", \".\")"
+    "    data[\"image_path\"] = data[\"image_path\"].replace(\"MVTEC_det\", \".\")\n",
+    "    data[\"bbox\"] = normalize_bbox(\n",
+    "        bbox=data[\"bbox\"],\n",
+    "        width=data[\"width\"],\n",
+    "        height=data[\"height\"]\n",
+    "    )"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -198,7 +221,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -213,7 +236,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -240,7 +263,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 57,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -279,7 +302,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
@@ -288,7 +311,7 @@
        "Text(0.5, 0, 'Good/Defect')"
       ]
      },
-     "execution_count": 58,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     },