{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e37789ff",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "from bs4 import BeautifulSoup\n",
    "import numpy as np \n",
    "import pandas as pd\n",
    "import os\n",
    "from time import perf_counter\n",
    "import cv2\n",
    "import tensorflow as tf\n",
    "from random import randint "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "4f0f6e16",
   "metadata": {},
   "outputs": [],
   "source": [
    "images_path= 'data/images'\n",
    "anno_path= 'data/annotations'\n",
    "size=128"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "a8bfd197",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(300, 400, 4)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x21d7461d190>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "img= plt.imread(f'data/images/Cars{randint(0,400)}.png')\n",
    "print(img.shape)\n",
    "plt.imshow(img)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f812021c",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "07b66c3c",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "bca3feab",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_data(imgDir, annoDir, size=size):\n",
    "    start= perf_counter()\n",
    "    df={\n",
    "    'image':[],\n",
    "    'box':[]\n",
    "    }\n",
    "    images= os.listdir(images_path)   #read file names in directory\n",
    "    for image in images:\n",
    "        plate= annoDir+'/'+image[:-3]+'xml'    \n",
    "        image= imgDir+'/'+image\n",
    "        img2= plt.imread( image ) \n",
    "        #img2= cv2.cvtColor( img2, cv2.COLOR_BGR2GRAY)\n",
    "        img2= img2[:,:,0:3] #remove 4th axis from image  if not gray                         \n",
    "        \n",
    "       \n",
    "        \n",
    "        #img=cv2.resize(img, (int(size), int(size)))\n",
    "        \n",
    "        with open( plate, 'r') as f:\n",
    "            data= f.read()\n",
    "        \n",
    "        Bs = BeautifulSoup(data, \"xml\")\n",
    "        xmax = int (Bs.find('ymax').text)\n",
    "        xmin = int (Bs.find('ymin').text)\n",
    "        ymax = int (Bs.find('xmax').text)\n",
    "        ymin = int (Bs.find('xmin').text)\n",
    " \n",
    "        #\n",
    "        img=img2.copy()\n",
    "        df['image'].append( cv2.resize(img2, (size,size) ) )\n",
    "        #print(xmin,ymin, xmax, ymax)\n",
    "        img2= cv2.rectangle(img2,(ymin,xmin), (ymax,xmax), 10,0)\n",
    "        \n",
    "        \n",
    "        df['box'].append(cv2.resize(img,(size,size)))\n",
    "        \n",
    "    print(perf_counter()-start)\n",
    "    return df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0cfa8705",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e5f809a1",
   "metadata": {},
   "outputs": [
    {
     "ename": "error",
     "evalue": "OpenCV(4.5.2) :-1: error: (-5:Bad argument) in function 'rectangle'\n> Overload resolution failed:\n>  - Layout of the output array img is incompatible with cv::Mat (step[ndims-1] != elemsize or step[1] != elemsize*nchannels)\n>  - Expected Ptr<cv::UMat> for argument 'img'\n>  - Layout of the output array img is incompatible with cv::Mat (step[ndims-1] != elemsize or step[1] != elemsize*nchannels)\n>  - Expected Ptr<cv::UMat> for argument 'img'\n",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31merror\u001b[0m                                     Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-7-2835cbfb1d44>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdf\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mget_data\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mimages_path\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0manno_path\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32m<ipython-input-6-026e652442f6>\u001b[0m in \u001b[0;36mget_data\u001b[1;34m(imgDir, annoDir, size)\u001b[0m\n\u001b[0;32m     30\u001b[0m         \u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'image'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m \u001b[0mcv2\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresize\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mimg2\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0msize\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0msize\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m)\u001b[0m \u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     31\u001b[0m         \u001b[1;31m#print(xmin,ymin, xmax, ymax)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 32\u001b[1;33m         \u001b[0mimg2\u001b[0m\u001b[1;33m=\u001b[0m \u001b[0mcv2\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrectangle\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mimg2\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mymin\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mxmin\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mymax\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mxmax\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m10\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     33\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     34\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31merror\u001b[0m: OpenCV(4.5.2) :-1: error: (-5:Bad argument) in function 'rectangle'\n> Overload resolution failed:\n>  - Layout of the output array img is incompatible with cv::Mat (step[ndims-1] != elemsize or step[1] != elemsize*nchannels)\n>  - Expected Ptr<cv::UMat> for argument 'img'\n>  - Layout of the output array img is incompatible with cv::Mat (step[ndims-1] != elemsize or step[1] != elemsize*nchannels)\n>  - Expected Ptr<cv::UMat> for argument 'img'\n"
     ]
    }
   ],
   "source": [
    "df=get_data(images_path, anno_path)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f49a1309",
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.imshow(df['box'][125])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9dc4039a",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9038cd96",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "78d26b99",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5d7f36ef",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "263b9ef2",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "b730032e",
   "metadata": {},
   "outputs": [],
   "source": [
    "dff=pd.DataFrame(df)\n",
    "x_train= np.array(dff.image[:300].values.tolist()).astype('float32')\n",
    "y_train= np.array(dff.box[:300].values.tolist()).astype('float32')\n",
    "x_test=  np.array(dff.box[300:].values.tolist()).astype('float32')\n",
    "y_test=  np.array(dff.box[300:].values.tolist()).astype('float32')\n",
    "del dff"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "69185862",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3382755f",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ebcabb06",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d90d8ba8",
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import Conv2D, MaxPool2D, Dropout, BatchNormalization, Activation, Conv2DTranspose, concatenate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e2e76900",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5414495b",
   "metadata": {},
   "outputs": [],
   "source": [
    "def model(InputImage,dropout=0.25):\n",
    "    \n",
    "    \n",
    "    ################Encoder###########making image smaller(making convnets)\n",
    "    c1=Conv2D( 32, (3,3),kernel_initializer = 'he_normal', padding='same')(InputImage)\n",
    "    c1=BatchNormalization()(c1)\n",
    "    c1=Activation('relu')(c1)\n",
    "    c2=Activation('relu')(c1)\n",
    "    p1=MaxPool2D((2,2))(c1)\n",
    "    p1=Dropout(dropout)(p1)\n",
    "    \n",
    "    c2=Conv2D( 64, (3,3),kernel_initializer = 'he_normal', padding='same')(p1)\n",
    "    c2=BatchNormalization()(c2)\n",
    "    c2=Activation('relu')(c2)\n",
    "    p2=MaxPool2D( (2,2) )(c2)\n",
    "    p2=Dropout(dropout)(p2)\n",
    "    \n",
    "    c3=Conv2D( 128, (3,3),kernel_initializer = 'he_normal', padding='same')(p2)\n",
    "    c3=BatchNormalization()(c3)\n",
    "    c3=Activation('relu')(c3)\n",
    "    \n",
    "    \n",
    "    ################Decoder###########making small image big(img from convnets)\n",
    "    \n",
    "    u1= Conv2DTranspose(64,(3,3), strides=(2,2), padding='same')(c3)\n",
    "    u1= concatenate([u1,c2])\n",
    "    u1= Dropout(dropout)(u1)\n",
    "    c6=Conv2D( 64, (3,3), padding='same')(u1)\n",
    "    c6=BatchNormalization()(c6)\n",
    "    c6=Activation('relu')(c6)\n",
    "    \n",
    "    \n",
    "    u2= Conv2DTranspose(32,(3,3), strides=(2,2), padding='same')(c6)\n",
    "    u2= concatenate([u2,c1])\n",
    "    u2= Dropout(dropout)(u2)\n",
    "    c7=Conv2D( 32, (3,3), padding='same')(u2)\n",
    "    c7=BatchNormalization()(c7)\n",
    "    c7=Activation('relu')(c7)\n",
    "    \n",
    "    output = Conv2D(3,(1,1), activation='sigmoid')(c7)\n",
    "    \n",
    "    m= tf.keras.Model([InputImage], [output])\n",
    "    return m\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "96d5dd0d",
   "metadata": {},
   "outputs": [],
   "source": [
    "inputs= tf.keras.layers.Input((size,size,3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "73047d25",
   "metadata": {},
   "outputs": [],
   "source": [
    "my= model(inputs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "803cd428",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"functional_1\"\n",
      "__________________________________________________________________________________________________\n",
      "Layer (type)                    Output Shape         Param #     Connected to                     \n",
      "==================================================================================================\n",
      "input_1 (InputLayer)            [(None, 128, 128, 3) 0                                            \n",
      "__________________________________________________________________________________________________\n",
      "conv2d (Conv2D)                 (None, 128, 128, 32) 896         input_1[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization (BatchNorma (None, 128, 128, 32) 128         conv2d[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "activation (Activation)         (None, 128, 128, 32) 0           batch_normalization[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling2d (MaxPooling2D)    (None, 64, 64, 32)   0           activation[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "dropout (Dropout)               (None, 64, 64, 32)   0           max_pooling2d[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_1 (Conv2D)               (None, 64, 64, 64)   18496       dropout[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_1 (BatchNor (None, 64, 64, 64)   256         conv2d_1[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "activation_2 (Activation)       (None, 64, 64, 64)   0           batch_normalization_1[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling2d_1 (MaxPooling2D)  (None, 32, 32, 64)   0           activation_2[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "dropout_1 (Dropout)             (None, 32, 32, 64)   0           max_pooling2d_1[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_2 (Conv2D)               (None, 32, 32, 128)  73856       dropout_1[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_2 (BatchNor (None, 32, 32, 128)  512         conv2d_2[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "activation_3 (Activation)       (None, 32, 32, 128)  0           batch_normalization_2[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_transpose (Conv2DTranspo (None, 64, 64, 64)   73792       activation_3[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "concatenate (Concatenate)       (None, 64, 64, 128)  0           conv2d_transpose[0][0]           \n",
      "                                                                 activation_2[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "dropout_2 (Dropout)             (None, 64, 64, 128)  0           concatenate[0][0]                \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_3 (Conv2D)               (None, 64, 64, 64)   73792       dropout_2[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_3 (BatchNor (None, 64, 64, 64)   256         conv2d_3[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "activation_4 (Activation)       (None, 64, 64, 64)   0           batch_normalization_3[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_transpose_1 (Conv2DTrans (None, 128, 128, 32) 18464       activation_4[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "concatenate_1 (Concatenate)     (None, 128, 128, 64) 0           conv2d_transpose_1[0][0]         \n",
      "                                                                 activation[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "dropout_3 (Dropout)             (None, 128, 128, 64) 0           concatenate_1[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_4 (Conv2D)               (None, 128, 128, 32) 18464       dropout_3[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_4 (BatchNor (None, 128, 128, 32) 128         conv2d_4[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "activation_5 (Activation)       (None, 128, 128, 32) 0           batch_normalization_4[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_5 (Conv2D)               (None, 128, 128, 3)  99          activation_5[0][0]               \n",
      "==================================================================================================\n",
      "Total params: 279,139\n",
      "Trainable params: 278,499\n",
      "Non-trainable params: 640\n",
      "__________________________________________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "my.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "2678dbd0",
   "metadata": {},
   "outputs": [],
   "source": [
    "my.compile(optimizer = 'Adam', loss = 'binary_crossentropy', metrics = ['accuracy'] )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "c79f6977",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/40\n",
      "10/10 [==============================] - 120s 12s/step - loss: 0.6170 - accuracy: 0.3626 - val_loss: 3.4285 - val_accuracy: 0.3598\n",
      "Epoch 2/40\n",
      "10/10 [==============================] - 159s 16s/step - loss: 0.5454 - accuracy: 0.4273 - val_loss: 3.6893 - val_accuracy: 0.3808\n",
      "Epoch 3/40\n",
      "10/10 [==============================] - 85s 9s/step - loss: 0.5272 - accuracy: 0.4790 - val_loss: 2.3057 - val_accuracy: 0.3917\n",
      "Epoch 4/40\n",
      "10/10 [==============================] - 79s 8s/step - loss: 0.5185 - accuracy: 0.5169 - val_loss: 1.4349 - val_accuracy: 0.4053\n",
      "Epoch 5/40\n",
      "10/10 [==============================] - 92s 9s/step - loss: 0.5137 - accuracy: 0.5501 - val_loss: 1.0818 - val_accuracy: 0.4513\n",
      "Epoch 6/40\n",
      "10/10 [==============================] - 94s 9s/step - loss: 0.5101 - accuracy: 0.5716 - val_loss: 0.9405 - val_accuracy: 0.4641\n",
      "Epoch 7/40\n",
      "10/10 [==============================] - 101s 10s/step - loss: 0.5085 - accuracy: 0.5932 - val_loss: 0.7569 - val_accuracy: 0.5156\n",
      "Epoch 8/40\n",
      "10/10 [==============================] - 101s 10s/step - loss: 0.5062 - accuracy: 0.6065 - val_loss: 0.7242 - val_accuracy: 0.5079\n",
      "Epoch 9/40\n",
      "10/10 [==============================] - 89s 9s/step - loss: 0.5059 - accuracy: 0.6271 - val_loss: 0.6386 - val_accuracy: 0.5453\n",
      "Epoch 10/40\n",
      "10/10 [==============================] - 85s 9s/step - loss: 0.5037 - accuracy: 0.6257 - val_loss: 0.5939 - val_accuracy: 0.5683\n",
      "Epoch 11/40\n",
      "10/10 [==============================] - 161s 16s/step - loss: 0.5037 - accuracy: 0.6403 - val_loss: 0.6208 - val_accuracy: 0.5776\n",
      "Epoch 12/40\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-14-6d17cbbbf79d>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mh\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmy\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx_train\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my_train\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m40\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverbose\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalidation_data\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx_test\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my_test\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\tensorflow\\python\\keras\\engine\\training.py\u001b[0m in \u001b[0;36m_method_wrapper\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m    106\u001b[0m   \u001b[1;32mdef\u001b[0m \u001b[0m_method_wrapper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    107\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_in_multi_worker_mode\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m  \u001b[1;31m# pylint: disable=protected-access\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 108\u001b[1;33m       \u001b[1;32mreturn\u001b[0m \u001b[0mmethod\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    109\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    110\u001b[0m     \u001b[1;31m# Running inside `run_distribute_coordinator` already.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\tensorflow\\python\\keras\\engine\\training.py\u001b[0m in \u001b[0;36mfit\u001b[1;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[0;32m   1096\u001b[0m                 batch_size=batch_size):\n\u001b[0;32m   1097\u001b[0m               \u001b[0mcallbacks\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mon_train_batch_begin\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstep\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1098\u001b[1;33m               \u001b[0mtmp_logs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtrain_function\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0miterator\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1099\u001b[0m               \u001b[1;32mif\u001b[0m \u001b[0mdata_handler\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshould_sync\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1100\u001b[0m                 \u001b[0mcontext\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0masync_wait\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\tensorflow\\python\\eager\\def_function.py\u001b[0m in \u001b[0;36m__call__\u001b[1;34m(self, *args, **kwds)\u001b[0m\n\u001b[0;32m    778\u001b[0m       \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    779\u001b[0m         \u001b[0mcompiler\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;34m\"nonXla\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 780\u001b[1;33m         \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    781\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    782\u001b[0m       \u001b[0mnew_tracing_count\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_tracing_count\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\tensorflow\\python\\eager\\def_function.py\u001b[0m in \u001b[0;36m_call\u001b[1;34m(self, *args, **kwds)\u001b[0m\n\u001b[0;32m    805\u001b[0m       \u001b[1;31m# In this case we have created variables on the first call, so we run the\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    806\u001b[0m       \u001b[1;31m# defunned version which is guaranteed to never create variables.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 807\u001b[1;33m       \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_stateless_fn\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m  \u001b[1;31m# pylint: disable=not-callable\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    808\u001b[0m     \u001b[1;32melif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_stateful_fn\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    809\u001b[0m       \u001b[1;31m# Release the lock early so that multiple threads can perform the call\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\tensorflow\\python\\eager\\function.py\u001b[0m in \u001b[0;36m__call__\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   2827\u001b[0m     \u001b[1;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_lock\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2828\u001b[0m       \u001b[0mgraph_function\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_maybe_define_function\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2829\u001b[1;33m     \u001b[1;32mreturn\u001b[0m \u001b[0mgraph_function\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_filtered_call\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m  \u001b[1;31m# pylint: disable=protected-access\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   2830\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2831\u001b[0m   \u001b[1;33m@\u001b[0m\u001b[0mproperty\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\tensorflow\\python\\eager\\function.py\u001b[0m in \u001b[0;36m_filtered_call\u001b[1;34m(self, args, kwargs, cancellation_manager)\u001b[0m\n\u001b[0;32m   1841\u001b[0m       \u001b[0;31m`\u001b[0m\u001b[0margs\u001b[0m\u001b[0;31m`\u001b[0m \u001b[1;32mand\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m`\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;31m`\u001b[0m\u001b[1;33m.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1842\u001b[0m     \"\"\"\n\u001b[1;32m-> 1843\u001b[1;33m     return self._call_flat(\n\u001b[0m\u001b[0;32m   1844\u001b[0m         [t for t in nest.flatten((args, kwargs), expand_composites=True)\n\u001b[0;32m   1845\u001b[0m          if isinstance(t, (ops.Tensor,\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\tensorflow\\python\\eager\\function.py\u001b[0m in \u001b[0;36m_call_flat\u001b[1;34m(self, args, captured_inputs, cancellation_manager)\u001b[0m\n\u001b[0;32m   1921\u001b[0m         and executing_eagerly):\n\u001b[0;32m   1922\u001b[0m       \u001b[1;31m# No tape is watching; skip to running the function.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1923\u001b[1;33m       return self._build_call_outputs(self._inference_function.call(\n\u001b[0m\u001b[0;32m   1924\u001b[0m           ctx, args, cancellation_manager=cancellation_manager))\n\u001b[0;32m   1925\u001b[0m     forward_backward = self._select_forward_and_backward_functions(\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\tensorflow\\python\\eager\\function.py\u001b[0m in \u001b[0;36mcall\u001b[1;34m(self, ctx, args, cancellation_manager)\u001b[0m\n\u001b[0;32m    543\u001b[0m       \u001b[1;32mwith\u001b[0m \u001b[0m_InterpolateFunctionError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    544\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mcancellation_manager\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 545\u001b[1;33m           outputs = execute.execute(\n\u001b[0m\u001b[0;32m    546\u001b[0m               \u001b[0mstr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msignature\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    547\u001b[0m               \u001b[0mnum_outputs\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_num_outputs\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\tensorflow\\python\\eager\\execute.py\u001b[0m in \u001b[0;36mquick_execute\u001b[1;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[0m\n\u001b[0;32m     57\u001b[0m   \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     58\u001b[0m     \u001b[0mctx\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mensure_initialized\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 59\u001b[1;33m     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,\n\u001b[0m\u001b[0;32m     60\u001b[0m                                         inputs, attrs, num_outputs)\n\u001b[0;32m     61\u001b[0m   \u001b[1;32mexcept\u001b[0m \u001b[0mcore\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_NotOkStatusException\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "h=my.fit(x_train, y_train, epochs=40, verbose=1, validation_data=(x_test, y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0f2bed2f",
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(20,5))\n",
    "plt.subplot(121)\n",
    "plt.plot(h.history['accuracy'] )\n",
    "plt.plot(h.history['val_accuracy'])\n",
    "plt.legend(['Train Accuracy','Test Accuracy'])\n",
    "plt.subplot(122)\n",
    "plt.plot(h.history['loss'])\n",
    "plt.plot(h.history['val_loss'])\n",
    "plt.legend(['Train Loss','Test Loss'])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5b8d3ce6",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9bb43b81",
   "metadata": {},
   "outputs": [],
   "source": [
    "a=df['image'][311].reshape(-1,128,128,3)\n",
    "b=df['box'][311].reshape(-1,128,128,3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "155f02e8",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fcbb5df9",
   "metadata": {},
   "outputs": [],
   "source": [
    "b= randint(0,450)\n",
    "a=df['image'][b].reshape(-1,128,128,3)\n",
    "b=df['box'][b].reshape(-1,128,128,3)\n",
    "plt.figure(figsize=(15,5))\n",
    "plt.subplot(131)\n",
    "plt.imshow(a.reshape(128,128,3))\n",
    "plt.subplot(132)\n",
    "plt.imshow(b.reshape(128,128,3))\n",
    "plt.subplot(133)\n",
    "plt.imshow(my.predict(a).reshape(128,128,3))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "68ab8d44",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}