{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.layers import Conv2D, MaxPooling2D, GlobalAveragePooling2D\n",
    "from keras.layers import Input, concatenate, Conv2D, MaxPooling2D, Conv2DTranspose\n",
    "from keras.optimizers import Adam\n",
    "from keras.callbacks import ModelCheckpoint\n",
    "from keras import backend as K\n",
    "#KERAS_BACKEND=tensorflow\n",
    "#set \"KERAS_BACKEND=tensorflow\"\n",
    "from __future__ import print_function\n",
    "import os\n",
    "import numpy as np\n",
    "from skimage.io import imsave, imread\n",
    "from keras.models import Model\n",
    "from skimage.transform import resize\n",
    "from skimage.io import imsave\n",
    "import cv2\n",
    "from skimage.transform import resize\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "\n",
    "data_path = 'raw/'        \n",
    "image_rows = 420\n",
    "image_cols = 580"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "def create_train_data():\n",
    "    train_data_path = os.path.join(data_path, 'train')\n",
    "    images = os.listdir(train_data_path)\n",
    "    total = len(images) // 2\n",
    "\n",
    "    imgs = np.ndarray((total, image_rows, image_cols), dtype=np.uint8)\n",
    "    imgs_mask = np.ndarray((total, image_rows, image_cols), dtype=np.uint8)\n",
    "\n",
    "    i = 0\n",
    "    print('-'*30)\n",
    "    print('Creating training images...')\n",
    "    print('-'*30)\n",
    "    for image_name in images:\n",
    "        if 'mask' in image_name:\n",
    "            continue\n",
    "        image_mask_name = image_name.split('.')[0] + '_mask.tif'\n",
    "        img = imread(os.path.join(train_data_path, image_name), as_grey=True)\n",
    "        img_mask = imread(os.path.join(train_data_path, image_mask_name), as_grey=True)\n",
    "\n",
    "        img = np.array([img])\n",
    "        img_mask = np.array([img_mask])\n",
    "\n",
    "        imgs[i] = img\n",
    "        imgs_mask[i] = img_mask\n",
    "\n",
    "        #if i % 100 == 0:\n",
    "        #   print('Done: {0}/{1} images'.format(i, total))\n",
    "        i += 1\n",
    "    print('Loading done.............................')\n",
    "\n",
    "    np.save('imgs_train.npy', imgs)\n",
    "    np.save('imgs_mask_train.npy', imgs_mask)\n",
    "    print('Saving to .npy files done.')\n",
    "\n",
    "\n",
    "def load_train_data():\n",
    "    imgs_train = np.load('imgs_train.npy')\n",
    "    imgs_mask_train = np.load('imgs_mask_train.npy')\n",
    "    return imgs_train, imgs_mask_train\n",
    "\n",
    "\n",
    "def create_test_data():\n",
    "    train_data_path = os.path.join(data_path, 'test2')\n",
    "    images = os.listdir(train_data_path)\n",
    "    total = len(images)\n",
    "\n",
    "    imgs = np.ndarray((total, image_rows, image_cols), dtype=np.uint8)\n",
    "    imgs_id = np.ndarray((total, ), dtype=np.int32)\n",
    "\n",
    "    i = 0\n",
    "    print('-'*30)\n",
    "    print('Creating test images...')\n",
    "    print('-'*30)\n",
    "    for image_name in images:\n",
    "        img_id = int(image_name.split('.')[0])\n",
    "        img = imread(os.path.join(train_data_path, image_name), as_grey=True)\n",
    "\n",
    "        img = np.array([img])\n",
    "\n",
    "        imgs[i] = img\n",
    "        imgs_id[i] = img_id\n",
    "\n",
    "        i += 1\n",
    "    print('Loading done..............')\n",
    "\n",
    "    np.save('imgs_test2.npy', imgs)\n",
    "    np.save('imgs_id_test2.npy', imgs_id)\n",
    "    print('Saving to .npy files done.')\n",
    "\n",
    "\n",
    "def load_test_data():\n",
    "    imgs_test = np.load('imgs_test2.npy')\n",
    "    imgs_id = np.load('imgs_id_test2.npy')\n",
    "    return imgs_test, imgs_id\n",
    "\n",
    "create_train_data()\n",
    "create_test_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "__________________________________________________________________________________________________\n",
      "Layer (type)                    Output Shape         Param #     Connected to                     \n",
      "==================================================================================================\n",
      "input_1 (InputLayer)            (None, 96, 96, 1)    0                                            \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_1 (Conv2D)               (None, 96, 96, 32)   320         input_1[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_2 (Conv2D)               (None, 96, 96, 32)   9248        conv2d_1[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling2d_1 (MaxPooling2D)  (None, 48, 48, 32)   0           conv2d_2[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_3 (Conv2D)               (None, 48, 48, 64)   18496       max_pooling2d_1[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_4 (Conv2D)               (None, 48, 48, 64)   36928       conv2d_3[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling2d_2 (MaxPooling2D)  (None, 24, 24, 64)   0           conv2d_4[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_5 (Conv2D)               (None, 24, 24, 128)  73856       max_pooling2d_2[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_6 (Conv2D)               (None, 24, 24, 128)  147584      conv2d_5[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling2d_3 (MaxPooling2D)  (None, 12, 12, 128)  0           conv2d_6[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_7 (Conv2D)               (None, 12, 12, 256)  295168      max_pooling2d_3[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_8 (Conv2D)               (None, 12, 12, 256)  590080      conv2d_7[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling2d_4 (MaxPooling2D)  (None, 6, 6, 256)    0           conv2d_8[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_9 (Conv2D)               (None, 6, 6, 512)    1180160     max_pooling2d_4[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_10 (Conv2D)              (None, 6, 6, 512)    2359808     conv2d_9[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_transpose_1 (Conv2DTrans (None, 12, 12, 256)  524544      conv2d_10[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "concatenate_1 (Concatenate)     (None, 12, 12, 512)  0           conv2d_transpose_1[0][0]         \n",
      "                                                                 conv2d_8[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_11 (Conv2D)              (None, 12, 12, 256)  1179904     concatenate_1[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_12 (Conv2D)              (None, 12, 12, 256)  590080      conv2d_11[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_transpose_2 (Conv2DTrans (None, 24, 24, 128)  131200      conv2d_12[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "concatenate_2 (Concatenate)     (None, 24, 24, 256)  0           conv2d_transpose_2[0][0]         \n",
      "                                                                 conv2d_6[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_13 (Conv2D)              (None, 24, 24, 128)  295040      concatenate_2[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_14 (Conv2D)              (None, 24, 24, 128)  147584      conv2d_13[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_transpose_3 (Conv2DTrans (None, 48, 48, 64)   32832       conv2d_14[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "concatenate_3 (Concatenate)     (None, 48, 48, 128)  0           conv2d_transpose_3[0][0]         \n",
      "                                                                 conv2d_4[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_15 (Conv2D)              (None, 48, 48, 64)   73792       concatenate_3[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_16 (Conv2D)              (None, 48, 48, 64)   36928       conv2d_15[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_transpose_4 (Conv2DTrans (None, 96, 96, 32)   8224        conv2d_16[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "concatenate_4 (Concatenate)     (None, 96, 96, 64)   0           conv2d_transpose_4[0][0]         \n",
      "                                                                 conv2d_2[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_17 (Conv2D)              (None, 96, 96, 32)   18464       concatenate_4[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_18 (Conv2D)              (None, 96, 96, 32)   9248        conv2d_17[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_19 (Conv2D)              (None, 96, 96, 1)    33          conv2d_18[0][0]                  \n",
      "==================================================================================================\n",
      "Total params: 7,759,521\n",
      "Trainable params: 7,759,521\n",
      "Non-trainable params: 0\n",
      "__________________________________________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "#from keras.models import Model\n",
    "K.set_image_data_format('channels_last')  # TF dimension ordering in this code\n",
    "\n",
    "img_rows = 96\n",
    "img_cols = 96\n",
    "\n",
    "smooth = 1.\n",
    "\n",
    "def dice_coef(y_true, y_pred):\n",
    "    y_true_f = K.flatten(y_true)\n",
    "    y_pred_f = K.flatten(y_pred)\n",
    "    intersection = K.sum(y_true_f * y_pred_f)\n",
    "    return (2. * intersection + smooth) / (K.sum(y_true_f) + K.sum(y_pred_f) + smooth)\n",
    "\n",
    "\n",
    "def dice_coef_loss(y_true, y_pred):\n",
    "    return -dice_coef(y_true, y_pred)\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "inputs = Input((img_rows, img_cols, 1))\n",
    "conv1 = Conv2D(32, (3, 3), activation='relu', padding='same')(inputs)\n",
    "conv1 = Conv2D(32, (3, 3), activation='relu', padding='same')(conv1)\n",
    "pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)\n",
    "\n",
    "conv2 = Conv2D(64, (3, 3), activation='relu', padding='same')(pool1)\n",
    "conv2 = Conv2D(64, (3, 3), activation='relu', padding='same')(conv2)\n",
    "pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)\n",
    "\n",
    "conv3 = Conv2D(128, (3, 3), activation='relu', padding='same')(pool2)\n",
    "conv3 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv3)\n",
    "pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)\n",
    "\n",
    "conv4 = Conv2D(256, (3, 3), activation='relu', padding='same')(pool3)\n",
    "conv4 = Conv2D(256, (3, 3), activation='relu', padding='same')(conv4)\n",
    "pool4 = MaxPooling2D(pool_size=(2, 2))(conv4)\n",
    "\n",
    "conv5 = Conv2D(512, (3, 3), activation='relu', padding='same')(pool4)\n",
    "conv5 = Conv2D(512, (3, 3), activation='relu', padding='same')(conv5)\n",
    "\n",
    "up6 = concatenate([Conv2DTranspose(256, (2, 2), strides=(2, 2), padding='same')(conv5), conv4], axis=3)\n",
    "conv6 = Conv2D(256, (3, 3), activation='relu', padding='same')(up6)\n",
    "conv6 = Conv2D(256, (3, 3), activation='relu', padding='same')(conv6)\n",
    "\n",
    "up7 = concatenate([Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same')(conv6), conv3], axis=3)\n",
    "conv7 = Conv2D(128, (3, 3), activation='relu', padding='same')(up7)\n",
    "conv7 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv7)\n",
    "\n",
    "up8 = concatenate([Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same')(conv7), conv2], axis=3)\n",
    "conv8 = Conv2D(64, (3, 3), activation='relu', padding='same')(up8)\n",
    "conv8 = Conv2D(64, (3, 3), activation='relu', padding='same')(conv8)\n",
    "\n",
    "up9 = concatenate([Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same')(conv8), conv1], axis=3)\n",
    "conv9 = Conv2D(32, (3, 3), activation='relu', padding='same')(up9)\n",
    "conv9 = Conv2D(32, (3, 3), activation='relu', padding='same')(conv9)\n",
    "\n",
    "conv10 = Conv2D(1, (1, 1), activation='sigmoid')(conv9)\n",
    "\n",
    "model = Model(inputs=[inputs], outputs=[conv10])\n",
    "model.compile(optimizer=Adam(lr=1e-5), loss=dice_coef_loss, metrics=[dice_coef])\n",
    "\n",
    "model_checkpoint = ModelCheckpoint('weights.h5', monitor='val_loss', save_best_only=True)\n",
    "model.fit(imgs_train, imgs_mask_train, batch_size=32, nb_epoch=20, verbose=1, shuffle=True,\n",
    "              validation_split=0.2,\n",
    "              callbacks=[model_checkpoint])\n",
    "\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "def preprocess(imgs):\n",
    "    imgs_p = np.ndarray((imgs.shape[0], img_rows, img_cols), dtype=np.uint8)\n",
    "    for i in range(imgs.shape[0]):\n",
    "        imgs_p[i] = resize(imgs[i], (img_cols, img_rows), preserve_range=True)\n",
    "\n",
    "    imgs_p = imgs_p[..., np.newaxis]\n",
    "    return imgs_p\n",
    "\n",
    "\n",
    "def train_and_predict():\n",
    "    print('-'*30)\n",
    "    print('Loading and preprocessing train data...')\n",
    "    print('-'*30)\n",
    "    imgs_train, imgs_mask_train = load_train_data()\n",
    "\n",
    "    imgs_train = preprocess(imgs_train)\n",
    "    imgs_mask_train = preprocess(imgs_mask_train)\n",
    "\n",
    "    imgs_train = imgs_train.astype('float32')\n",
    "    mean = np.mean(imgs_train)  # mean for data centering\n",
    "    std = np.std(imgs_train)  # std for data normalization\n",
    "\n",
    "    imgs_train -= mean\n",
    "    imgs_train /= std\n",
    "\n",
    "    imgs_mask_train = imgs_mask_train.astype('float32')\n",
    "    imgs_mask_train /= 255.  # scale masks to [0, 1]\n",
    "\n",
    "    print('-'*30)\n",
    "    print('Creating and compiling model...')\n",
    "    print('-'*30)\n",
    "    \n",
    "    model_checkpoint = ModelCheckpoint('weights.h5', monitor='val_loss', save_best_only=True)\n",
    "\n",
    "    print('-'*30)\n",
    "    print('Fitting model...')\n",
    "    print('-'*30)\n",
    "    model.fit(imgs_train, imgs_mask_train, batch_size=32, nb_epoch=20, verbose=1, shuffle=True,\n",
    "              validation_split=0.2,\n",
    "              callbacks=[model_checkpoint])\n",
    "\n",
    "    print('-'*30)\n",
    "    print('Loading and preprocessing test data...')\n",
    "    print('-'*30)\n",
    "    imgs_test, imgs_id_test = load_test_data()\n",
    "    imgs_test = preprocess(imgs_test)\n",
    "\n",
    "    imgs_test = imgs_test.astype('float32')\n",
    "    imgs_test -= mean\n",
    "    imgs_test /= std\n",
    "\n",
    "    # loading the trained weights for loading in the predict function\n",
    "    print('-'*30)\n",
    "    print('Loading saved weights...')\n",
    "    print('-'*30)\n",
    "    model.load_weights('weights.h5')\n",
    "\n",
    "    # creating the masks and saving the image masks as numpy \n",
    "    print('-'*30)\n",
    "    print('Predicting masks on test data...')\n",
    "    print('-'*30)\n",
    "    imgs_mask_test = model.predict(imgs_test, verbose=1)\n",
    "    np.save('imgs_mask_test.npy', imgs_mask_test)\n",
    "\n",
    "    print('-' * 30)\n",
    "    print('Saving predicted masks to files...')\n",
    "    print('-' * 30)\n",
    "    \n",
    "def predict():\n",
    "    create_test_data()\n",
    "    imgs_train, imgs_mask_train = load_train_data()\n",
    "\n",
    "    imgs_train = preprocess(imgs_train)\n",
    "    imgs_mask_train = preprocess(imgs_mask_train)\n",
    "\n",
    "    imgs_train = imgs_train.astype('float32')\n",
    "    mean = np.mean(imgs_train)  # mean for data centering\n",
    "    std = np.std(imgs_train)  # std for data normalization\n",
    "\n",
    "    imgs_train -= mean\n",
    "    imgs_train /= std\n",
    "\n",
    "    imgs_mask_train = imgs_mask_train.astype('float32')\n",
    "    imgs_mask_train /= 255.  # scale masks to [0, 1]\n",
    "\n",
    "    imgs_test, imgs_id_test = load_test_data()\n",
    "    imgs_test = preprocess(imgs_test)\n",
    "\n",
    "    imgs_test = imgs_test.astype('float32')\n",
    "    imgs_test -= mean\n",
    "    imgs_test /= std\n",
    "    # loading the trained weights for loading in the predict function\n",
    "    print('-'*30)\n",
    "    print('Loading saved weights...')\n",
    "    print('-'*30)\n",
    "    model.load_weights('weights.h5')\n",
    "\n",
    "    # creating the masks and saving the image masks as numpy \n",
    "    print('-'*30)\n",
    "    print('Predicting masks on test data...')\n",
    "    print('-'*30)\n",
    "    imgs_mask_test = model.predict(imgs_test, verbose=1)\n",
    "    np.save('imgs_mask_test2.npy', imgs_mask_test)\n",
    "\n",
    "    print('-' * 30)\n",
    "    print('Saving predicted masks to files...')\n",
    "    print('-' * 30)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "------------------------------\n",
      "Creating test images...\n",
      "------------------------------\n",
      "Loading done..............\n",
      "Saving to .npy files done.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\akuppal\\AppData\\Local\\Continuum\\anaconda3\\lib\\site-packages\\skimage\\transform\\_warps.py:84: UserWarning: The default mode, 'constant', will be changed to 'reflect' in skimage 0.15.\n",
      "  warn(\"The default mode, 'constant', will be changed to 'reflect' in \"\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "------------------------------\n",
      "Loading saved weights...\n",
      "------------------------------\n",
      "------------------------------\n",
      "Predicting masks on test data...\n",
      "------------------------------\n",
      "5/5 [==============================] - 0s 74ms/step\n",
      "------------------------------\n",
      "Saving predicted masks to files...\n",
      "------------------------------\n"
     ]
    }
   ],
   "source": [
    "#confirming the backend for keras\n",
    "K.backend()\n",
    "predict()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "------------------------------\n",
      "Loading and preprocessing train data...\n",
      "------------------------------\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\akuppal\\AppData\\Local\\Continuum\\anaconda3\\lib\\site-packages\\skimage\\transform\\_warps.py:84: UserWarning: The default mode, 'constant', will be changed to 'reflect' in skimage 0.15.\n",
      "  warn(\"The default mode, 'constant', will be changed to 'reflect' in \"\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "------------------------------\n",
      "Creating and compiling model...\n",
      "------------------------------\n",
      "------------------------------\n",
      "Fitting model...\n",
      "------------------------------\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\akuppal\\AppData\\Local\\Continuum\\anaconda3\\lib\\site-packages\\ipykernel_launcher.py:40: UserWarning: The `nb_epoch` argument in `fit` has been renamed `epochs`.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train on 4508 samples, validate on 1127 samples\n",
      "Epoch 1/20\n",
      "4508/4508 [==============================] - 807s 179ms/step - loss: -0.0254 - dice_coef: 0.0254 - val_loss: -0.0204 - val_dice_coef: 0.0204\n",
      "Epoch 2/20\n",
      "4508/4508 [==============================] - 836s 186ms/step - loss: -0.0316 - dice_coef: 0.0316 - val_loss: -0.0373 - val_dice_coef: 0.0373\n",
      "Epoch 3/20\n",
      "4508/4508 [==============================] - 802s 178ms/step - loss: -0.1837 - dice_coef: 0.1837 - val_loss: -0.1925 - val_dice_coef: 0.1925\n",
      "Epoch 4/20\n",
      "4508/4508 [==============================] - 805s 179ms/step - loss: -0.3027 - dice_coef: 0.3027 - val_loss: -0.1510 - val_dice_coef: 0.1510\n",
      "Epoch 5/20\n",
      "4508/4508 [==============================] - 776s 172ms/step - loss: -0.3649 - dice_coef: 0.3649 - val_loss: -0.2540 - val_dice_coef: 0.2540\n",
      "Epoch 6/20\n",
      "4508/4508 [==============================] - 794s 176ms/step - loss: -0.4051 - dice_coef: 0.4051 - val_loss: -0.2782 - val_dice_coef: 0.2782\n",
      "Epoch 7/20\n",
      "4508/4508 [==============================] - 859s 191ms/step - loss: -0.4313 - dice_coef: 0.4313 - val_loss: -0.3146 - val_dice_coef: 0.3146\n",
      "Epoch 8/20\n",
      "4508/4508 [==============================] - 764s 169ms/step - loss: -0.4491 - dice_coef: 0.4491 - val_loss: -0.2968 - val_dice_coef: 0.2968\n",
      "Epoch 9/20\n",
      "4508/4508 [==============================] - 772s 171ms/step - loss: -0.4568 - dice_coef: 0.4568 - val_loss: -0.3381 - val_dice_coef: 0.3381\n",
      "Epoch 10/20\n",
      "4508/4508 [==============================] - 775s 172ms/step - loss: -0.4745 - dice_coef: 0.4745 - val_loss: -0.3454 - val_dice_coef: 0.3454\n",
      "Epoch 11/20\n",
      "4508/4508 [==============================] - 805s 179ms/step - loss: -0.4825 - dice_coef: 0.4825 - val_loss: -0.3590 - val_dice_coef: 0.3590\n",
      "Epoch 12/20\n",
      "4508/4508 [==============================] - 824s 183ms/step - loss: -0.5043 - dice_coef: 0.5043 - val_loss: -0.3540 - val_dice_coef: 0.3540\n",
      "Epoch 13/20\n",
      "4508/4508 [==============================] - 793s 176ms/step - loss: -0.5091 - dice_coef: 0.5091 - val_loss: -0.3483 - val_dice_coef: 0.3483\n",
      "Epoch 14/20\n",
      "4508/4508 [==============================] - 892s 198ms/step - loss: -0.5265 - dice_coef: 0.5265 - val_loss: -0.3760 - val_dice_coef: 0.3760\n",
      "Epoch 15/20\n",
      "4508/4508 [==============================] - 778s 173ms/step - loss: -0.5342 - dice_coef: 0.5342 - val_loss: -0.3876 - val_dice_coef: 0.3876\n",
      "Epoch 16/20\n",
      "4508/4508 [==============================] - 762s 169ms/step - loss: -0.5437 - dice_coef: 0.5437 - val_loss: -0.3499 - val_dice_coef: 0.3499\n",
      "Epoch 17/20\n",
      "4508/4508 [==============================] - 749s 166ms/step - loss: -0.5530 - dice_coef: 0.5530 - val_loss: -0.3603 - val_dice_coef: 0.3603\n",
      "Epoch 18/20\n",
      "4508/4508 [==============================] - 814s 181ms/step - loss: -0.5611 - dice_coef: 0.5611 - val_loss: -0.3732 - val_dice_coef: 0.3732\n",
      "Epoch 19/20\n",
      "4508/4508 [==============================] - 781s 173ms/step - loss: -0.5713 - dice_coef: 0.5713 - val_loss: -0.3648 - val_dice_coef: 0.3648\n",
      "Epoch 20/20\n",
      "4508/4508 [==============================] - 3604s 799ms/step - loss: -0.5745 - dice_coef: 0.5745 - val_loss: -0.3913 - val_dice_coef: 0.3913\n",
      "------------------------------\n",
      "Loading and preprocessing test data...\n",
      "------------------------------\n",
      "------------------------------\n",
      "Loading saved weights...\n",
      "------------------------------\n",
      "------------------------------\n",
      "Predicting masks on test data...\n",
      "------------------------------\n",
      "5508/5508 [==============================] - 315s 57ms/step\n",
      "------------------------------\n",
      "Saving predicted masks to files...\n",
      "------------------------------\n"
     ]
    }
   ],
   "source": [
    "#training the model and predicting\n",
    "#train_and_predict()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x26ade7b75c0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x26adc02cef0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x26adcb744a8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import cv2\n",
    "\n",
    "test_array = np.load('imgs_test2.npy')\n",
    "mask_array = np.load('imgs_mask_test2.npy')\n",
    "#test_array = np.load('imgs_test.npy')\n",
    "#mask_array = np.load('imgs_mask_test.npy')\n",
    "\n",
    "test_id = np.load('imgs_id_test2.npy')\n",
    "#test_id = np.load('imgs_id_test.npy')\n",
    "img_idx = 2\n",
    "\n",
    "test = test_array[img_idx].astype('float32')\n",
    "mask = mask_array[img_idx].astype('float32')\n",
    "mask = np.array(mask * 255, dtype = np.uint8)\n",
    "\n",
    "resized_mask = cv2.resize(mask, (test.shape[1],test.shape[0]))\n",
    "\n",
    "# contour detection in resized_mask\n",
    "ret,thresh = cv2.threshold(resized_mask,127,255,0)\n",
    "im2, contours, hierarchy = cv2.findContours(thresh,cv2.RETR_LIST,cv2.CHAIN_APPROX_NONE)\n",
    "\n",
    "# apply the overlay\n",
    "output = test.copy()\n",
    "output = cv2.cvtColor(output,cv2.COLOR_GRAY2BGR)\n",
    "\n",
    "# draw the contour\n",
    "cv2.drawContours(output, contours, -1, (0,0,255), 3)\n",
    "plt.imshow(test,cmap='gray')\n",
    "plt.show()\n",
    "plt.imshow(thresh,cmap='gray')\n",
    "plt.show()\n",
    "plt.imshow(output,cmap='gray')\n",
    "plt.show()\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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}