COCO data visualization

COCO_data.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Populating the interactive namespace from numpy and matplotlib\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import json\n",
    "import pandas as pd\n",
    "import pprint\n",
    "%pylab inline\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.image as mpimg\n",
    "import matplotlib.patches as patches\n",
    "plt.rcParams[\"figure.figsize\"] = (20,15)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Подгружаем аннотации"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "filenames_list = os.listdir('val2017')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"/Users/iccomplex/Desktop/JetsonNano/coco_xml/annotations/captions_val2017.json\", \"r\") as read_file:\n",
    "    caption_data = json.load(read_file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"/Users/iccomplex/Desktop/JetsonNano/coco_xml/annotations/instances_val2017.json\", \"r\") as read_file:\n",
    "    annotation_data = json.load(read_file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "#caption_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "#annotation_data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Смотрим на данные из COCO"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_images_info = pd.DataFrame(annotation_data['images'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "#df_images_info.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_images_data = pd.DataFrame(annotation_data['annotations'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_images_cat = pd.DataFrame(annotation_data['categories'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "#df_images_cat[:20]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "#df_images_data[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_all_data = df_images_data.merge(df_images_info, left_on='image_id', right_on='id')\n",
    "df_all_data = df_all_data.merge(df_images_cat, left_on='category_id', right_on='id')\n",
    "df_all_data_boat = df_all_data[df_all_data['id']==9]\n",
    "#df_all_data_boat.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Пример изображения и bound box"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "image_id = 543043"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_temp = df_all_data_boat[df_all_data_boat['image_id']==image_id]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'000000543043.jpg'"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_temp.iloc[0]['file_name']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "img = mpimg.imread(f'val2017/{df_temp.iloc[0][\"file_name\"]}')\n",
    "fig, ax = plt.subplots()\n",
    "ax.imshow(img)\n",
    "for i in range(len(df_temp)):\n",
    "    bbox_coord = df_temp.iloc[i][\"bbox\"]\n",
    "    rect = patches.Rectangle((bbox_coord[0], bbox_coord[1]), bbox_coord[2], bbox_coord[3], linewidth=1, edgecolor='r', facecolor='none')\n",
    "    ax.add_patch(rect)\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}