Ex6.SampleSolution-DomainAdaptionAutoencoder.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "3c8d5a65",
   "metadata": {},
   "source": [
    "<img src=\"https://www.th-koeln.de/img/logo.svg\" style=\"float:right;\" width=\"200\">"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6aa99fd9",
   "metadata": {},
   "source": [
    "# Musterlösung / Sample solution \n",
    "## 6th exercise: <font color=\"#C70039\">Domain Adaption with Autoencoders</font>\n",
    "* Course: AML\n",
    "* Lecturer: <a href=\"https://www.gernotheisenberg.de/\">Gernot Heisenberg</a>\n",
    "* Author of notebook: <a href=\"https://www.gernotheisenberg.de/\">Gernot Heisenberg</a>\n",
    "* Date:   29.06.2022\n",
    "\n",
    "---------------------------------\n",
    "\n",
    "### Description \n",
    "This is one implementation example to demo the image reconstruction using autoencoders for domain adaption. \n",
    "PLease do not miss to try different optimizers and losses.\n",
    "\n",
    "---------------------------------"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "a50f3435",
   "metadata": {},
   "outputs": [],
   "source": [
    "from matplotlib import pyplot as plt\n",
    "import numpy as np\n",
    "import cv2\n",
    "import tensorflow as tf\n",
    "from tensorflow.keras.preprocessing.image import img_to_array\n",
    "from tensorflow.keras.layers import Conv2D, MaxPooling2D, UpSampling2D\n",
    "from tensorflow.keras.models import Sequential\n",
    "import os\n",
    "from   tqdm import tqdm\n",
    "import time"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "df24b693",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 50/50 [00:00<00:00, 396.86it/s]\n",
      "100%|██████████| 50/50 [00:00<00:00, 436.83it/s]\n"
     ]
    }
   ],
   "source": [
    "SIZE=256\n",
    "\n",
    "# import input img\n",
    "input_img_data=[]\n",
    "input_path = './data/heisenberg_heisenberg/gernot/'\n",
    "files=os.listdir(input_path)\n",
    "# read all images in the folder (different rotations and flips of the original)\n",
    "for i in tqdm(files):\n",
    "    img=cv2.imread(input_path+'/'+i,1)   #Change 0 to 1 for color images\n",
    "    img=cv2.resize(img,(SIZE, SIZE))\n",
    "    input_img_data.append(img_to_array(img))\n",
    "# -----------------------------------------  \n",
    "# import output_img\n",
    "output_img_data=[]\n",
    "output_path = './data/heisenberg_heisenberg/walter/'\n",
    "files=os.listdir(output_path)\n",
    "# read all images in the folder (same rotations and flips as img)\n",
    "for i in tqdm(files):\n",
    "    img=cv2.imread(output_path+'/'+i,1)  #Change 0 to 1 for color images\n",
    "    img=cv2.resize(img,(SIZE, SIZE))\n",
    "    output_img_data.append(img_to_array(img))\n",
    "\n",
    "input_img_array = np.reshape(input_img_data, (len(input_img_data), SIZE, SIZE, 3))\n",
    "input_img_array = input_img_array.astype('float32') / 255. # normalize\n",
    "output_img_array= np.reshape(output_img_data, (len(output_img_data), SIZE, SIZE, 3))\n",
    "output_img_array = output_img_array.astype('float32') / 255. # normalize"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "bd91e964",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Original image for prediction of output_img \n",
    "# this one does not belong to the training set\n",
    "test_img_data=[]\n",
    "\n",
    "test_img=cv2.imread('./data/heisenberg_heisenberg/gernot-heisenberg-original.jpg', 1)   #Change 0 to 1 for color images\n",
    "test_img = cv2.cvtColor(test_img, cv2.COLOR_BGR2RGB)#Changing BGR to RGB to show images in true colors\n",
    "test_img=cv2.resize(test_img,(SIZE, SIZE))\n",
    "test_img_data.append(img_to_array(test_img))\n",
    "\n",
    "test_img_array = np.reshape(test_img_data, (len(test_img_data), SIZE, SIZE, 3))\n",
    "test_img_array = test_img_array.astype('float32') / 255. # normalize\n",
    "\n",
    "# set the start time\n",
    "# later needed for calculating the computation time\n",
    "start=time.time()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "20dd69aa",
   "metadata": {},
   "source": [
    "## Build the autoencoder-decoder model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "6ae50643",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential_2\"\n",
      "_________________________________________________________________\n",
      " Layer (type)                Output Shape              Param #   \n",
      "=================================================================\n",
      " conv2d_14 (Conv2D)          (None, 256, 256, 32)      896       \n",
      "                                                                 \n",
      " max_pooling2d_6 (MaxPooling  (None, 128, 128, 32)     0         \n",
      " 2D)                                                             \n",
      "                                                                 \n",
      " conv2d_15 (Conv2D)          (None, 128, 128, 8)       2312      \n",
      "                                                                 \n",
      " max_pooling2d_7 (MaxPooling  (None, 64, 64, 8)        0         \n",
      " 2D)                                                             \n",
      "                                                                 \n",
      " conv2d_16 (Conv2D)          (None, 64, 64, 8)         584       \n",
      "                                                                 \n",
      " max_pooling2d_8 (MaxPooling  (None, 32, 32, 8)        0         \n",
      " 2D)                                                             \n",
      "                                                                 \n",
      " conv2d_17 (Conv2D)          (None, 32, 32, 8)         584       \n",
      "                                                                 \n",
      " up_sampling2d_6 (UpSampling  (None, 64, 64, 8)        0         \n",
      " 2D)                                                             \n",
      "                                                                 \n",
      " conv2d_18 (Conv2D)          (None, 64, 64, 8)         584       \n",
      "                                                                 \n",
      " up_sampling2d_7 (UpSampling  (None, 128, 128, 8)      0         \n",
      " 2D)                                                             \n",
      "                                                                 \n",
      " conv2d_19 (Conv2D)          (None, 128, 128, 32)      2336      \n",
      "                                                                 \n",
      " up_sampling2d_8 (UpSampling  (None, 256, 256, 32)     0         \n",
      " 2D)                                                             \n",
      "                                                                 \n",
      " conv2d_20 (Conv2D)          (None, 256, 256, 3)       867       \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 8,163\n",
      "Trainable params: 8,163\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n",
      "Epoch 1/50\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "Input \u001b[0;32mIn [11]\u001b[0m, in \u001b[0;36m<cell line: 25>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     21\u001b[0m \u001b[38;5;66;03m#callbacks = [tf.keras.callbacks.TensorBoard(log_dir='einstein_logs')]\u001b[39;00m\n\u001b[1;32m     22\u001b[0m \n\u001b[1;32m     23\u001b[0m \u001b[38;5;66;03m# fit the model of input_img to output_img \u001b[39;00m\n\u001b[1;32m     24\u001b[0m epochs \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m50\u001b[39m\n\u001b[0;32m---> 25\u001b[0m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43minput_img_array\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43moutput_img_array\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mepochs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mepochs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mshuffle\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[38;5;66;03m#, callbacks=callbacks)\u001b[39;00m\n\u001b[1;32m     27\u001b[0m \u001b[38;5;66;03m# print out the computation time\u001b[39;00m\n\u001b[1;32m     28\u001b[0m finish\u001b[38;5;241m=\u001b[39mtime\u001b[38;5;241m.\u001b[39mtime()\n",
      "File \u001b[0;32m~/opt/anaconda3/envs/aml/lib/python3.9/site-packages/keras/utils/traceback_utils.py:64\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m     62\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m     63\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 64\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     65\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:  \u001b[38;5;66;03m# pylint: disable=broad-except\u001b[39;00m\n\u001b[1;32m     66\u001b[0m   filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n",
      "File \u001b[0;32m~/opt/anaconda3/envs/aml/lib/python3.9/site-packages/keras/engine/training.py:1409\u001b[0m, in \u001b[0;36mModel.fit\u001b[0;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[1;32m   1402\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m tf\u001b[38;5;241m.\u001b[39mprofiler\u001b[38;5;241m.\u001b[39mexperimental\u001b[38;5;241m.\u001b[39mTrace(\n\u001b[1;32m   1403\u001b[0m     \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtrain\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[1;32m   1404\u001b[0m     epoch_num\u001b[38;5;241m=\u001b[39mepoch,\n\u001b[1;32m   1405\u001b[0m     step_num\u001b[38;5;241m=\u001b[39mstep,\n\u001b[1;32m   1406\u001b[0m     batch_size\u001b[38;5;241m=\u001b[39mbatch_size,\n\u001b[1;32m   1407\u001b[0m     _r\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m):\n\u001b[1;32m   1408\u001b[0m   callbacks\u001b[38;5;241m.\u001b[39mon_train_batch_begin(step)\n\u001b[0;32m-> 1409\u001b[0m   tmp_logs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain_function\u001b[49m\u001b[43m(\u001b[49m\u001b[43miterator\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1410\u001b[0m   \u001b[38;5;28;01mif\u001b[39;00m data_handler\u001b[38;5;241m.\u001b[39mshould_sync:\n\u001b[1;32m   1411\u001b[0m     context\u001b[38;5;241m.\u001b[39masync_wait()\n",
      "File \u001b[0;32m~/opt/anaconda3/envs/aml/lib/python3.9/site-packages/tensorflow/python/util/traceback_utils.py:150\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    148\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    149\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 150\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    151\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    152\u001b[0m   filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n",
      "File \u001b[0;32m~/opt/anaconda3/envs/aml/lib/python3.9/site-packages/tensorflow/python/eager/def_function.py:915\u001b[0m, in \u001b[0;36mFunction.__call__\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    912\u001b[0m compiler \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mxla\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jit_compile \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnonXla\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    914\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m OptionalXlaContext(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jit_compile):\n\u001b[0;32m--> 915\u001b[0m   result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    917\u001b[0m new_tracing_count \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mexperimental_get_tracing_count()\n\u001b[1;32m    918\u001b[0m without_tracing \u001b[38;5;241m=\u001b[39m (tracing_count \u001b[38;5;241m==\u001b[39m new_tracing_count)\n",
      "File \u001b[0;32m~/opt/anaconda3/envs/aml/lib/python3.9/site-packages/tensorflow/python/eager/def_function.py:980\u001b[0m, in \u001b[0;36mFunction._call\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    976\u001b[0m     \u001b[38;5;28;01mpass\u001b[39;00m  \u001b[38;5;66;03m# Fall through to cond-based initialization.\u001b[39;00m\n\u001b[1;32m    977\u001b[0m   \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    978\u001b[0m     \u001b[38;5;66;03m# Lifting succeeded, so variables are initialized and we can run the\u001b[39;00m\n\u001b[1;32m    979\u001b[0m     \u001b[38;5;66;03m# stateless function.\u001b[39;00m\n\u001b[0;32m--> 980\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_stateless_fn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    981\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    982\u001b[0m   _, _, filtered_flat_args \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    983\u001b[0m       \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_stateful_fn\u001b[38;5;241m.\u001b[39m_function_spec\u001b[38;5;241m.\u001b[39mcanonicalize_function_inputs(  \u001b[38;5;66;03m# pylint: disable=protected-access\u001b[39;00m\n\u001b[1;32m    984\u001b[0m           \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwds))\n",
      "File \u001b[0;32m~/opt/anaconda3/envs/aml/lib/python3.9/site-packages/tensorflow/python/eager/function.py:2453\u001b[0m, in \u001b[0;36mFunction.__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   2450\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_lock:\n\u001b[1;32m   2451\u001b[0m   (graph_function,\n\u001b[1;32m   2452\u001b[0m    filtered_flat_args) \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_maybe_define_function(args, kwargs)\n\u001b[0;32m-> 2453\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mgraph_function\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_flat\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   2454\u001b[0m \u001b[43m    \u001b[49m\u001b[43mfiltered_flat_args\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcaptured_inputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgraph_function\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcaptured_inputs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/opt/anaconda3/envs/aml/lib/python3.9/site-packages/tensorflow/python/eager/function.py:1860\u001b[0m, in \u001b[0;36mConcreteFunction._call_flat\u001b[0;34m(self, args, captured_inputs, cancellation_manager)\u001b[0m\n\u001b[1;32m   1856\u001b[0m possible_gradient_type \u001b[38;5;241m=\u001b[39m gradients_util\u001b[38;5;241m.\u001b[39mPossibleTapeGradientTypes(args)\n\u001b[1;32m   1857\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (possible_gradient_type \u001b[38;5;241m==\u001b[39m gradients_util\u001b[38;5;241m.\u001b[39mPOSSIBLE_GRADIENT_TYPES_NONE\n\u001b[1;32m   1858\u001b[0m     \u001b[38;5;129;01mand\u001b[39;00m executing_eagerly):\n\u001b[1;32m   1859\u001b[0m   \u001b[38;5;66;03m# No tape is watching; skip to running the function.\u001b[39;00m\n\u001b[0;32m-> 1860\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_build_call_outputs(\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_inference_function\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcall\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1861\u001b[0m \u001b[43m      \u001b[49m\u001b[43mctx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcancellation_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcancellation_manager\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[1;32m   1862\u001b[0m forward_backward \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_select_forward_and_backward_functions(\n\u001b[1;32m   1863\u001b[0m     args,\n\u001b[1;32m   1864\u001b[0m     possible_gradient_type,\n\u001b[1;32m   1865\u001b[0m     executing_eagerly)\n\u001b[1;32m   1866\u001b[0m forward_function, args_with_tangents \u001b[38;5;241m=\u001b[39m forward_backward\u001b[38;5;241m.\u001b[39mforward()\n",
      "File \u001b[0;32m~/opt/anaconda3/envs/aml/lib/python3.9/site-packages/tensorflow/python/eager/function.py:497\u001b[0m, in \u001b[0;36m_EagerDefinedFunction.call\u001b[0;34m(self, ctx, args, cancellation_manager)\u001b[0m\n\u001b[1;32m    495\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m _InterpolateFunctionError(\u001b[38;5;28mself\u001b[39m):\n\u001b[1;32m    496\u001b[0m   \u001b[38;5;28;01mif\u001b[39;00m cancellation_manager \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 497\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m \u001b[43mexecute\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexecute\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    498\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mstr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msignature\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mname\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    499\u001b[0m \u001b[43m        \u001b[49m\u001b[43mnum_outputs\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[43m_num_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    500\u001b[0m \u001b[43m        \u001b[49m\u001b[43minputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    501\u001b[0m \u001b[43m        \u001b[49m\u001b[43mattrs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattrs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    502\u001b[0m \u001b[43m        \u001b[49m\u001b[43mctx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mctx\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    503\u001b[0m   \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    504\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m execute\u001b[38;5;241m.\u001b[39mexecute_with_cancellation(\n\u001b[1;32m    505\u001b[0m         \u001b[38;5;28mstr\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msignature\u001b[38;5;241m.\u001b[39mname),\n\u001b[1;32m    506\u001b[0m         num_outputs\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_num_outputs,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    509\u001b[0m         ctx\u001b[38;5;241m=\u001b[39mctx,\n\u001b[1;32m    510\u001b[0m         cancellation_manager\u001b[38;5;241m=\u001b[39mcancellation_manager)\n",
      "File \u001b[0;32m~/opt/anaconda3/envs/aml/lib/python3.9/site-packages/tensorflow/python/eager/execute.py:54\u001b[0m, in \u001b[0;36mquick_execute\u001b[0;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[0m\n\u001b[1;32m     52\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m     53\u001b[0m   ctx\u001b[38;5;241m.\u001b[39mensure_initialized()\n\u001b[0;32m---> 54\u001b[0m   tensors \u001b[38;5;241m=\u001b[39m \u001b[43mpywrap_tfe\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mTFE_Py_Execute\u001b[49m\u001b[43m(\u001b[49m\u001b[43mctx\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_handle\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mop_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     55\u001b[0m \u001b[43m                                      \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mattrs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnum_outputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     56\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m core\u001b[38;5;241m.\u001b[39m_NotOkStatusException \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m     57\u001b[0m   \u001b[38;5;28;01mif\u001b[39;00m name \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "model = Sequential()\n",
    "\n",
    "model.add(Conv2D(32, (3, 3), activation='relu', padding='same', input_shape=(SIZE, SIZE, 3)))\n",
    "model.add(MaxPooling2D((2, 2), padding='same'))\n",
    "model.add(Conv2D(8, (3, 3), activation='relu', padding='same'))\n",
    "model.add(MaxPooling2D((2, 2), padding='same'))\n",
    "model.add(Conv2D(8, (3, 3), activation='relu', padding='same'))\n",
    "model.add(MaxPooling2D((2, 2), padding='same'))\n",
    "     \n",
    "model.add(Conv2D(8, (3, 3), activation='relu', padding='same'))\n",
    "model.add(UpSampling2D((2, 2)))\n",
    "model.add(Conv2D(8, (3, 3), activation='relu', padding='same'))\n",
    "model.add(UpSampling2D((2, 2)))\n",
    "model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))\n",
    "model.add(UpSampling2D((2, 2)))\n",
    "model.add(Conv2D(3, (3, 3), activation='relu', padding='same'))\n",
    "\n",
    "model.compile(optimizer='adam', loss='mean_squared_error', metrics=['accuracy'])\n",
    "model.summary()\n",
    "\n",
    "#callbacks = [tf.keras.callbacks.TensorBoard(log_dir='einstein_logs')]\n",
    "\n",
    "# fit the model of input_img to output_img \n",
    "epochs = 50\n",
    "model.fit(input_img_array, output_img_array, epochs=epochs, shuffle=True)#, callbacks=callbacks)\n",
    "\n",
    "# print out the computation time\n",
    "finish=time.time()\n",
    "print('total computation time = ', finish-start)\n",
    "\n",
    "# save the model\n",
    "model.save(\"domain_adapt_autoenc_epochs.\" + str(epochs) + \".model\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "df2d2f78",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "output of test image\n",
      "1/1 [==============================] - 0s 407ms/step\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# predict the original image as test image, \n",
    "# since it did not belong to the training data.\n",
    "# if the domain was really adapted, then the result would look like output_img\n",
    "\n",
    "print(\"output of test image\")\n",
    "pred = model.predict(test_img_array)\n",
    "plt.imshow(pred[0].reshape(SIZE,SIZE,3))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9bb9fc43",
   "metadata": {},
   "outputs": [],
   "source": [
    "# save the model\n",
    "model.save(\"domain_adapt_autoenc_epochs.\" + str(epochs) + \".model\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "826bb252",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}