{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "# File renaming for consistency\n",
    "import os\n",
    "from os import path\n",
    "\n",
    "for count, filename in enumerate(os.listdir(\"deadlift2\")):\n",
    "    src = \"deadlift2/\" + filename\n",
    "    string = \"deadlift2/deadlift_\" + str(count) + \".jpg\"\n",
    "    os.rename(src, string)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "https://machinelearningmastery.com/how-to-develop-a-convolutional-neural-network-to-classify-photos-of-dogs-and-cats/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(549,) ()\n"
     ]
    }
   ],
   "source": [
    "from os import listdir\n",
    "from numpy import asarray\n",
    "from numpy import save\n",
    "from keras.preprocessing.image import load_img\n",
    "from keras.preprocessing.image import img_to_array\n",
    "\n",
    "folder = \"train/\"\n",
    "photos, labels = list(), list()\n",
    "\n",
    "for file in listdir(folder):\n",
    "    output = 0.0\n",
    "    if file.startswith(\"squat\"):\n",
    "        output = 1.0\n",
    "    if file.startswith(\"deadlift\"):\n",
    "        output = 2.0\n",
    "    photo = load_img(folder + file, target_size=(150,150))\n",
    "    photo = img_to_array\n",
    "    \n",
    "    photos.append(photo)\n",
    "    labels.append(output)\n",
    "photos = asarray(photos)\n",
    "labels = asarray(output)\n",
    "print(photos.shape, labels.shape)\n",
    "\n",
    "save(\"exercise_photos.npy\", photos)\n",
    "save(\"exercise_labels.npy\", photos)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(549,) (549,)\n"
     ]
    }
   ],
   "source": [
    "from numpy import load\n",
    "photos = load(\"exercise_photos.npy\",allow_pickle=True)\n",
    "labels = load(\"exercise_labels.npy\",allow_pickle=True)\n",
    "\n",
    "print(photos.shape, labels.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Directory Generation\n",
    "from os import makedirs\n",
    "dataset_home = \"dataset/\"\n",
    "subdirs = [\"train/\", \"test/\"]\n",
    "for subdir in subdirs:\n",
    "    # create label subdirectories\n",
    "    labeldirs = [\"bench/\", \"squat/\", \"deadlift/\"]\n",
    "    for labldir in labeldirs:\n",
    "        newdir = dataset_home + subdir + labldir\n",
    "        makedirs(newdir)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Segment into testing and training images\n",
    "import random\n",
    "from shutil import copyfile\n",
    "random.seed(1)\n",
    "ratio = 0.2\n",
    "dataset_home = \"dataset/\"\n",
    "src_directory = \"images/\"\n",
    "for file in listdir(src_directory):\n",
    "    src = src_directory + '/' + file\n",
    "    dst_dir = \"train/\"\n",
    "    if random.random() < ratio:\n",
    "        dst_dir = \"test/\"\n",
    "    if file.startswith(\"bench\"):\n",
    "        dst = dataset_home + dst_dir + \"bench/\" + file\n",
    "    elif file.startswith(\"squat\"):\n",
    "        dst = dataset_home + dst_dir + \"squat/\" + file\n",
    "    else:\n",
    "        dst = dataset_home + dst_dir + \"deadlift/\" + file\n",
    "    copyfile(src, dst)   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 448 images belonging to 3 classes.\n",
      "1\n",
      "Found 101 images belonging to 3 classes.\n"
     ]
    },
    {
     "ename": "InvalidArgumentError",
     "evalue": " Matrix size-incompatible: In[0]: [128,3], In[1]: [128,1]\n\t [[node gradient_tape/sequential_21/dense_41/MatMul (defined at <ipython-input-70-ca63fab2532d>:115) ]] [Op:__inference_train_function_17586]\n\nFunction call stack:\ntrain_function\n",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mInvalidArgumentError\u001b[0m                      Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-70-ca63fab2532d>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m    122\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    123\u001b[0m \u001b[1;31m# entry point, run the test harness\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 124\u001b[1;33m \u001b[0mrun_test_harness\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<ipython-input-70-ca63fab2532d>\u001b[0m in \u001b[0;36mrun_test_harness\u001b[1;34m()\u001b[0m\n\u001b[0;32m    113\u001b[0m         class_mode='categorical', batch_size=128, target_size=(150, 150))\n\u001b[0;32m    114\u001b[0m     \u001b[1;31m# fit model\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 115\u001b[1;33m     history = model.fit(train_it, steps_per_epoch=len(train_it),\n\u001b[0m\u001b[0;32m    116\u001b[0m         validation_data=test_it, validation_steps=len(test_it), epochs=20, verbose=0)\n\u001b[0;32m    117\u001b[0m     \u001b[1;31m# evaluate model\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\python38-64\\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;32mc:\\python38-64\\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;32mc:\\python38-64\\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;32mc:\\python38-64\\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    838\u001b[0m         \u001b[1;31m# Lifting succeeded, so variables are initialized and we can 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    839\u001b[0m         \u001b[1;31m# stateless function.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 840\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;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    841\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    842\u001b[0m       \u001b[0mcanon_args\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcanon_kwds\u001b[0m \u001b[1;33m=\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m\\\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\python38-64\\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;32mc:\\python38-64\\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;32mc:\\python38-64\\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;32mc:\\python38-64\\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;32mc:\\python38-64\\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;31mInvalidArgumentError\u001b[0m:  Matrix size-incompatible: In[0]: [128,3], In[1]: [128,1]\n\t [[node gradient_tape/sequential_21/dense_41/MatMul (defined at <ipython-input-70-ca63fab2532d>:115) ]] [Op:__inference_train_function_17586]\n\nFunction call stack:\ntrain_function\n"
     ]
    }
   ],
   "source": [
    "# Baseline CNN Model\n",
    "import sys\n",
    "from matplotlib import pyplot\n",
    "import keras\n",
    "from keras.utils import to_categorical\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Conv2D\n",
    "from keras.layers import MaxPooling2D\n",
    "from keras.layers import Dense\n",
    "from keras.layers import Flatten\n",
    "from keras.layers import Dropout\n",
    "from keras.optimizers import SGD\n",
    "from keras.preprocessing.image import ImageDataGenerator\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Dense, Dropout, Flatten\n",
    "from keras.layers import Conv2D, MaxPooling2D\n",
    "\n",
    " \n",
    "# one block VGG\n",
    "\"\"\"\n",
    "def define_model():\n",
    "    model = Sequential()\n",
    "    model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(150, 150, 3)))\n",
    "    model.add(MaxPooling2D((2, 2)))\n",
    "    model.add(Flatten())\n",
    "    model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n",
    "    model.add(Dense(1, activation='sigmoid'))\n",
    "    # compile model\n",
    "    opt = SGD(lr=0.001, momentum=0.9)\n",
    "    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n",
    "    return model\n",
    "\"\"\"\n",
    "\"\"\"\n",
    "# two block VGG\n",
    "def define_model():\n",
    "    model = Sequential()\n",
    "    model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(150, 150, 3)))\n",
    "    model.add(MaxPooling2D((2, 2)))\n",
    "    model.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\n",
    "    model.add(MaxPooling2D((2, 2)))\n",
    "    model.add(Flatten())\n",
    "    model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n",
    "    model.add(Dense(1, activation='sigmoid'))\n",
    "    # compile model\n",
    "    opt = SGD(lr=0.001, momentum=0.9)\n",
    "    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n",
    "    return model\n",
    "\"\"\"\n",
    "\n",
    "\n",
    "def define_model():\n",
    "    model = Sequential()\n",
    "    model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)))\n",
    "    model.add(MaxPooling2D((2, 2)))\n",
    "    model.add(Dropout(0.2))\n",
    "    model.add(Flatten())\n",
    "    model.add(Dense(128, activation='relu'))\n",
    "    model.add(Dense(1, activation='softmax'))\n",
    "    # compile model\n",
    "    #opt = SGD(lr=0.001, momentum=0.9)\n",
    "    model.compile(optimizer=keras.optimizers.Adam(), loss='categorical_crossentropy', metrics=['accuracy'])\n",
    "    return model\n",
    "\n",
    "\"\"\"\n",
    "# three block VGG\n",
    "def define_model():\n",
    "\n",
    "    cnn1 = Sequential()\n",
    "    cnn1.add(Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)))\n",
    "    cnn1.add(MaxPooling2D((2, 2)))\n",
    "    cnn1.add(Dropout(0.2))\n",
    "\n",
    "    cnn1.add(Flatten())\n",
    "\n",
    "    cnn1.add(Dense(128, activation='relu'))\n",
    "    cnn1.add(Dense(10, activation='softmax'))\n",
    "\n",
    "    cnn1.compile(loss=keras.losses.categorical_crossentropy,\n",
    "              optimizer=keras.optimizers.Adam(),\n",
    "              metrics=['accuracy'])\n",
    "    return cnn1\n",
    "\n",
    "\"\"\"\n",
    "\n",
    "# plot diagnostic learning curves\n",
    "def summarize_diagnostics(history):\n",
    "    # plot loss\n",
    "    pyplot.subplot(211)\n",
    "    pyplot.title('Cross Entropy Loss')\n",
    "    pyplot.plot(history.history['loss'], color='blue', label='train')\n",
    "    pyplot.plot(history.history['val_loss'], color='orange', label='test')\n",
    "    # plot accuracy\n",
    "    pyplot.subplot(212)\n",
    "    pyplot.title('Classification Accuracy')\n",
    "    pyplot.plot(history.history['accuracy'], color='blue', label='train')\n",
    "    pyplot.plot(history.history['val_accuracy'], color='orange', label='test')\n",
    "    # save plot to file\n",
    "    filename = sys.argv[0].split('/')[-1]\n",
    "    pyplot.savefig(filename + '_plot.png')\n",
    "    pyplot.close()\n",
    " \n",
    "# run the test harness for evaluating a model\n",
    "def run_test_harness():\n",
    "    # define model\n",
    "    model = define_model()\n",
    "    # create data generator\n",
    "    datagen = ImageDataGenerator(rescale=1.0/255.0)\n",
    "    # prepare iterators\n",
    "    train_it = datagen.flow_from_directory('dataset/train/',\n",
    "        class_mode='categorical', batch_size=128, target_size=(150, 150))\n",
    "    test_it = datagen.flow_from_directory('dataset/test/',\n",
    "        class_mode='categorical', batch_size=128, target_size=(150, 150))\n",
    "    # fit model\n",
    "    history = model.fit(train_it, steps_per_epoch=len(train_it),\n",
    "        validation_data=test_it, validation_steps=len(test_it), epochs=20, verbose=0)\n",
    "    # evaluate model\n",
    "    _, acc = model.evaluate_generator(test_it, steps=len(test_it), verbose=0)\n",
    "    print('> %.3f' % (acc * 100.0))\n",
    "    # learning curves\n",
    "    summarize_diagnostics(history)\n",
    " \n",
    "# entry point, run the test harness\n",
    "run_test_harness()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}