{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "9e3e0aed",
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.preprocessing.image import ImageDataGenerator\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Conv2D, MaxPooling2D\n",
    "from keras.layers import Activation, Dropout, Flatten, Dense\n",
    "from keras import backend as K\n",
    " \n",
    "img_width, img_height = 224, 224"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "976c0dc7",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_data_dir = 'v_data/train'\n",
    "validation_data_dir = 'v_data/test'\n",
    "nb_train_samples =400\n",
    "nb_validation_samples = 100\n",
    "epochs = 10\n",
    "batch_size = 16"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "9bf78481",
   "metadata": {},
   "outputs": [],
   "source": [
    "# check format\n",
    "\n",
    "\n",
    "if K.image_data_format() == 'channels_first':\n",
    "    input_shape = (3, img_width, img_height)\n",
    "else:\n",
    "    input_shape = (img_width, img_height, 3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a0663374",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = Sequential()\n",
    "model.add(Conv2D(32, (2, 2), input_shape=input_shape))\n",
    "model.add(Activation('relu'))\n",
    "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
    " \n",
    "model.add(Conv2D(32, (2, 2)))\n",
    "model.add(Activation('relu'))\n",
    "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
    " \n",
    "model.add(Conv2D(64, (2, 2)))\n",
    "model.add(Activation('relu'))\n",
    "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
    " \n",
    "model.add(Flatten())\n",
    "model.add(Dense(64))\n",
    "model.add(Activation('relu'))\n",
    "model.add(Dropout(0.5))\n",
    "model.add(Dense(1))\n",
    "model.add(Activation('sigmoid'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "6fadd7e5",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "model.compile(loss='binary_crossentropy',\n",
    "              optimizer='rmsprop',\n",
    "              metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "0bb1a7ba",
   "metadata": {},
   "outputs": [
    {
     "ename": "FileNotFoundError",
     "evalue": "[WinError 3] The system cannot find the path specified: 'v_data/train'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
      "Input \u001b[1;32mIn [7]\u001b[0m, in \u001b[0;36m<cell line: 9>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      1\u001b[0m train_datagen \u001b[38;5;241m=\u001b[39m ImageDataGenerator(\n\u001b[0;32m      2\u001b[0m     rescale\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1.\u001b[39m \u001b[38;5;241m/\u001b[39m \u001b[38;5;241m255\u001b[39m,\n\u001b[0;32m      3\u001b[0m     shear_range\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.2\u001b[39m,\n\u001b[0;32m      4\u001b[0m     zoom_range\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.2\u001b[39m,\n\u001b[0;32m      5\u001b[0m     horizontal_flip\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m      7\u001b[0m test_datagen \u001b[38;5;241m=\u001b[39m ImageDataGenerator(rescale\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1.\u001b[39m \u001b[38;5;241m/\u001b[39m \u001b[38;5;241m255\u001b[39m)\n\u001b[1;32m----> 9\u001b[0m train_generator \u001b[38;5;241m=\u001b[39m \u001b[43mtrain_datagen\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mflow_from_directory\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m     10\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtrain_data_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m     11\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtarget_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mimg_width\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mimg_height\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m     12\u001b[0m \u001b[43m    \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mbatch_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m     13\u001b[0m \u001b[43m    \u001b[49m\u001b[43mclass_mode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mbinary\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m     15\u001b[0m validation_generator \u001b[38;5;241m=\u001b[39m test_datagen\u001b[38;5;241m.\u001b[39mflow_from_directory(\n\u001b[0;32m     16\u001b[0m     validation_data_dir,\n\u001b[0;32m     17\u001b[0m     target_size\u001b[38;5;241m=\u001b[39m(img_width, img_height),\n\u001b[0;32m     18\u001b[0m     batch_size\u001b[38;5;241m=\u001b[39mbatch_size,\n\u001b[0;32m     19\u001b[0m     class_mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mbinary\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m     21\u001b[0m model\u001b[38;5;241m.\u001b[39mfit_generator(\n\u001b[0;32m     22\u001b[0m     train_generator,\n\u001b[0;32m     23\u001b[0m     steps_per_epoch\u001b[38;5;241m=\u001b[39mnb_train_samples \u001b[38;5;241m/\u001b[39m\u001b[38;5;241m/\u001b[39m batch_size,\n\u001b[0;32m     24\u001b[0m     epochs\u001b[38;5;241m=\u001b[39mepochs,\n\u001b[0;32m     25\u001b[0m     validation_data\u001b[38;5;241m=\u001b[39mvalidation_generator,\n\u001b[0;32m     26\u001b[0m     validation_steps\u001b[38;5;241m=\u001b[39mnb_validation_samples \u001b[38;5;241m/\u001b[39m\u001b[38;5;241m/\u001b[39m batch_size)\n",
      "File \u001b[1;32m~\\.conda\\envs\\py\\lib\\site-packages\\keras\\preprocessing\\image.py:1469\u001b[0m, in \u001b[0;36mImageDataGenerator.flow_from_directory\u001b[1;34m(self, directory, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, save_to_dir, save_prefix, save_format, follow_links, subset, interpolation, keep_aspect_ratio)\u001b[0m\n\u001b[0;32m   1386\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mflow_from_directory\u001b[39m(\u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m   1387\u001b[0m                         directory,\n\u001b[0;32m   1388\u001b[0m                         target_size\u001b[38;5;241m=\u001b[39m(\u001b[38;5;241m256\u001b[39m, \u001b[38;5;241m256\u001b[39m),\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1400\u001b[0m                         interpolation\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mnearest\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m   1401\u001b[0m                         keep_aspect_ratio\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[0;32m   1402\u001b[0m   \u001b[38;5;124;03m\"\"\"Takes the path to a directory & generates batches of augmented data.\u001b[39;00m\n\u001b[0;32m   1403\u001b[0m \n\u001b[0;32m   1404\u001b[0m \u001b[38;5;124;03m  Args:\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1467\u001b[0m \u001b[38;5;124;03m          and `y` is a numpy array of corresponding labels.\u001b[39;00m\n\u001b[0;32m   1468\u001b[0m \u001b[38;5;124;03m  \"\"\"\u001b[39;00m\n\u001b[1;32m-> 1469\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mDirectoryIterator\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   1470\u001b[0m \u001b[43m      \u001b[49m\u001b[43mdirectory\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1471\u001b[0m \u001b[43m      \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1472\u001b[0m \u001b[43m      \u001b[49m\u001b[43mtarget_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtarget_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1473\u001b[0m \u001b[43m      \u001b[49m\u001b[43mcolor_mode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcolor_mode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1474\u001b[0m \u001b[43m      \u001b[49m\u001b[43mkeep_aspect_ratio\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkeep_aspect_ratio\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1475\u001b[0m \u001b[43m      \u001b[49m\u001b[43mclasses\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mclasses\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1476\u001b[0m \u001b[43m      \u001b[49m\u001b[43mclass_mode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mclass_mode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1477\u001b[0m \u001b[43m      \u001b[49m\u001b[43mdata_format\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdata_format\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1478\u001b[0m \u001b[43m      \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mbatch_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1479\u001b[0m \u001b[43m      \u001b[49m\u001b[43mshuffle\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mshuffle\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1480\u001b[0m \u001b[43m      \u001b[49m\u001b[43mseed\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mseed\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1481\u001b[0m \u001b[43m      \u001b[49m\u001b[43msave_to_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msave_to_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1482\u001b[0m \u001b[43m      \u001b[49m\u001b[43msave_prefix\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msave_prefix\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1483\u001b[0m \u001b[43m      \u001b[49m\u001b[43msave_format\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msave_format\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1484\u001b[0m \u001b[43m      \u001b[49m\u001b[43mfollow_links\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfollow_links\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1485\u001b[0m \u001b[43m      \u001b[49m\u001b[43msubset\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msubset\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1486\u001b[0m \u001b[43m      \u001b[49m\u001b[43minterpolation\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minterpolation\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1487\u001b[0m \u001b[43m      \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdtype\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32m~\\.conda\\envs\\py\\lib\\site-packages\\keras\\preprocessing\\image.py:507\u001b[0m, in \u001b[0;36mDirectoryIterator.__init__\u001b[1;34m(self, directory, image_data_generator, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, data_format, save_to_dir, save_prefix, save_format, follow_links, subset, interpolation, keep_aspect_ratio, dtype)\u001b[0m\n\u001b[0;32m    505\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m classes:\n\u001b[0;32m    506\u001b[0m   classes \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m--> 507\u001b[0m   \u001b[38;5;28;01mfor\u001b[39;00m subdir \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28msorted\u001b[39m(\u001b[43mos\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlistdir\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdirectory\u001b[49m\u001b[43m)\u001b[49m):\n\u001b[0;32m    508\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39misdir(os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(directory, subdir)):\n\u001b[0;32m    509\u001b[0m       classes\u001b[38;5;241m.\u001b[39mappend(subdir)\n",
      "\u001b[1;31mFileNotFoundError\u001b[0m: [WinError 3] The system cannot find the path specified: 'v_data/train'"
     ]
    }
   ],
   "source": [
    "train_datagen = ImageDataGenerator(\n",
    "    rescale=1. / 255,\n",
    "    shear_range=0.2,\n",
    "    zoom_range=0.2,\n",
    "    horizontal_flip=True)\n",
    " \n",
    "test_datagen = ImageDataGenerator(rescale=1. / 255)\n",
    " \n",
    "train_generator = train_datagen.flow_from_directory(\n",
    "    train_data_dir,\n",
    "    target_size=(img_width, img_height),\n",
    "    batch_size=batch_size,\n",
    "    class_mode='binary')\n",
    " \n",
    "validation_generator = test_datagen.flow_from_directory(\n",
    "    validation_data_dir,\n",
    "    target_size=(img_width, img_height),\n",
    "    batch_size=batch_size,\n",
    "    class_mode='binary')\n",
    " \n",
    "model.fit_generator(\n",
    "    train_generator,\n",
    "    steps_per_epoch=nb_train_samples // batch_size,\n",
    "    epochs=epochs,\n",
    "    validation_data=validation_generator,\n",
    "    validation_steps=nb_validation_samples // batch_size)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "623ec03f",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "py",
   "language": "python",
   "name": "py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}