computer-vision/vision.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### vision"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7f50f04e1210>"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "from matplotlib import pyplot as plt\n",
    "\n",
    "import vision.io\n",
    "from vision.descriptor.avg_RGB import extract_average_rgb\n",
    "from vision.visualsearch import run_query\n",
    "\n",
    "x = vision.io.load_msrc('msrc/Images')\n",
    "extract_average_rgb(images=x)\n",
    "results = run_query(x)\n",
    "plt.imshow(results.query_image.pixels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.06465854988522113"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "results.precision_recall.ap"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7f35401c9a90>"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import cv2\n",
    "import numpy as np\n",
    "from matplotlib import pyplot as plt\n",
    "\n",
    "import vision.descriptor.spatial as spatial\n",
    "\n",
    "img = cv2.imread('sheep.png')[:,:,::-1]\n",
    "\n",
    "segments = spatial.grid_image(2, 2, img)\n",
    "print(len(segments))\n",
    "plt.imshow(segments[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import numpy as np\n",
    "from matplotlib import pyplot as plt\n",
    "\n",
    "import vision.descriptor.spatial as spatial\n",
    "\n",
    "img = cv2.imread('sheep.png')[:,:,::-1]\n",
    "\n",
    "segments = spatial.extract_spatial_average_rgb(2, 2, img)"
   ]
  }
 ],
 "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}