{"cells":[{"metadata":{"_uuid":"6a24661f1baec8ef9788f35aee8c5f8d7c695e4b"},"cell_type":"markdown","source":"**Based on** \n[https://www.kaggle.com/kmader/baseline-u-net-model-part-1](https://www.kaggle.com/kmader/baseline-u-net-model-part-1)"},{"metadata":{"trusted":true,"_uuid":"f402f5eade2cd5e309c79fc4e6cb28f920585823"},"cell_type":"code","source":"BATCH_SIZE = 4\nEDGE_CROP = 16\nNB_EPOCHS = 5\nGAUSSIAN_NOISE = 0.1\nUPSAMPLE_MODE = 'SIMPLE'\n# downsampling inside the network\nNET_SCALING = None\n# downsampling in preprocessing\nIMG_SCALING = (1, 1)\n# number of validation images to use\nVALID_IMG_COUNT = 400\n# maximum number of steps_per_epoch in training\nMAX_TRAIN_STEPS = 200\nAUGMENT_BRIGHTNESS = False","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7bc4c640cc0657f0de011463cbc3fc923345d363"},"cell_type":"code","source":"!ls ../input","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom skimage.io import imread\nimport matplotlib.pyplot as plt\nfrom skimage.segmentation import mark_boundaries\nfrom skimage.util.montage import montage2d as montage\nmontage_rgb = lambda x: np.stack([montage(x[:, :, :, i]) for i in range(x.shape[3])], -1)\nship_dir = '../input'\ntrain_image_dir = os.path.join(ship_dir, 'train_v2')\ntest_image_dir = os.path.join(ship_dir, 'test_v2')\nimport gc; gc.enable() # memory is tight\n\nfrom skimage.morphology import label\ndef multi_rle_encode(img):\n labels = label(img[:, :, 0])\n return [rle_encode(labels==k) for k in np.unique(labels[labels>0])]\n\n# ref: https://www.kaggle.com/paulorzp/run-length-encode-and-decode\ndef rle_encode(img):\n '''\n img: numpy array, 1 - mask, 0 - background\n Returns run length as string formated\n '''\n pixels = img.T.flatten()\n pixels = np.concatenate([[0], pixels, [0]])\n runs = np.where(pixels[1:] != pixels[:-1])[0] + 1\n runs[1::2] -= runs[::2]\n return ' '.join(str(x) for x in runs)\n\ndef rle_decode(mask_rle, shape=(768, 768)):\n '''\n mask_rle: run-length as string formated (start length)\n shape: (height,width) of array to return \n Returns numpy array, 1 - mask, 0 - background\n '''\n s = mask_rle.split()\n starts, lengths = [np.asarray(x, dtype=int) for x in (s[0:][::2], s[1:][::2])]\n starts -= 1\n ends = starts + lengths\n img = np.zeros(shape[0]*shape[1], dtype=np.uint8)\n for lo, hi in zip(starts, ends):\n img[lo:hi] = 1\n return img.reshape(shape).T # Needed to align to RLE direction\n\ndef masks_as_image(in_mask_list):\n # Take the individual ship masks and create a single mask array for all ships\n all_masks = np.zeros((768, 768), dtype = np.int16)\n #if isinstance(in_mask_list, list):\n for mask in in_mask_list:\n if isinstance(mask, str):\n all_masks += rle_decode(mask)\n return np.expand_dims(all_masks, -1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"845c77eba13ce4d4ce082e09fb3a175331479be5"},"cell_type":"code","source":"masks = pd.read_csv(os.path.join('../input/',\n 'train_ship_segmentations_v2.csv'))\nprint(masks.shape[0], 'masks found')\nprint(masks['ImageId'].value_counts().shape[0])\nmasks.head()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"f583577bce029cbd67d3bcdd8f4079de39e652a6"},"cell_type":"markdown","source":"# Make sure encode/decode works"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true,"scrolled":true},"cell_type":"code","source":"fig, (ax1, ax2) = plt.subplots(1, 2, figsize = (10, 5))\nrle_0 = masks.query('ImageId==\"00021ddc3.jpg\"')['EncodedPixels']\nimg_0 = masks_as_image(rle_0)\nax1.imshow(img_0[:, :, 0])\nax1.set_title('Image$_0$')\nrle_1 = multi_rle_encode(img_0)\nimg_1 = masks_as_image(rle_1)\nax2.imshow(img_1[:, :, 0])\nax2.set_title('Image$_1$')\nprint('Check Decoding->Encoding',\n 'RLE_0:', len(rle_0), '->',\n 'RLE_1:', len(rle_1))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f88043c56c0dfe39ad5c08189ed71ab5d3bbebd"},"cell_type":"markdown","source":"# Split into training and validation groups"},{"metadata":{"trusted":true,"_uuid":"ae1e0523bfe3ab7552ea5c5d8bd7dfe94ac61e90"},"cell_type":"code","source":"masks['ships'] = masks['EncodedPixels'].map(lambda c_row: 1 if isinstance(c_row, str) else 0)\nunique_img_ids = masks.groupby('ImageId').agg({'ships': 'sum'}).reset_index()\nunique_img_ids['has_ship'] = unique_img_ids['ships'].map(lambda x: 1.0 if x>0 else 0.0)\nunique_img_ids['has_ship_vec'] = unique_img_ids['has_ship'].map(lambda x: [x])\n# some files are too small/corrupt\nunique_img_ids['file_size_kb'] = unique_img_ids['ImageId'].map(lambda c_img_id: \n os.stat(os.path.join(train_image_dir, \n c_img_id)).st_size/1024)\nunique_img_ids = unique_img_ids[unique_img_ids['file_size_kb']>50] # keep only 50kb files\nunique_img_ids['file_size_kb'].hist()\nmasks.drop(['ships'], axis=1, inplace=True)\nunique_img_ids.sample(5)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"4e964fe17873d41f5b3d4b65d909c59078bc03db"},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\ntrain_ids, valid_ids = train_test_split(unique_img_ids, \n test_size = 0.3, \n stratify = unique_img_ids['ships'])\ntrain_df = pd.merge(masks, train_ids)\nvalid_df = pd.merge(masks, valid_ids)\nprint(train_df.shape[0], 'training masks')\nprint(valid_df.shape[0], 'validation masks')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"9c10daec0ddf195c4f23bd7e8270d8a6f1384e8d"},"cell_type":"markdown","source":"# Examine Number of Ship Images"},{"metadata":{"trusted":true,"_uuid":"f5537216785a8cb59a49f5db4a885f208b28c234"},"cell_type":"code","source":"train_df['ships'].hist()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"507b67ab2a4b83e43aecc875360ff1c4f805e2a8"},"cell_type":"markdown","source":"# Undersample Empty Images"},{"metadata":{"trusted":true,"_uuid":"951946c250061dc47c77987b3d8d3fa10e4502a0"},"cell_type":"code","source":"train_df['grouped_ship_count'] = train_df['ships'].map(lambda x: (x+1)//2).clip(0, 7)\ndef sample_ships(in_df, base_rep_val=1500):\n if in_df['ships'].values[0]==0:\n return in_df.sample(base_rep_val//3) # even more strongly undersample no ships\n else:\n return in_df.sample(base_rep_val, replace=(in_df.shape[0]=batch_size:\n yield np.stack(out_rgb, 0)/255.0, np.stack(out_mask, 0)\n out_rgb, out_mask=[], []","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7f6931d4d78c8d8943928c51818fde4df9a48438"},"cell_type":"code","source":"train_gen = make_image_gen(balanced_train_df)\ntrain_x, train_y = next(train_gen)\nprint('x', train_x.shape, train_x.min(), train_x.max())\nprint('y', train_y.shape, train_y.min(), train_y.max())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"450f927e8f349232bbb2fc1c4eff2347457de7aa"},"cell_type":"code","source":"fig, (ax1, ax2, ax3) = plt.subplots(1, 3, figsize = (30, 10))\nbatch_rgb = montage_rgb(train_x)\nbatch_seg = montage(train_y[:, :, :, 0])\nax1.imshow(batch_rgb)\nax1.set_title('Images')\nax2.imshow(batch_seg)\nax2.set_title('Segmentations')\nax3.imshow(mark_boundaries(batch_rgb, \n batch_seg.astype(int)))\nax3.set_title('Outlined Ships')\nfig.savefig('overview.png')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"3d70253ccb7bc55e07ff4d32b9ff79b718b28e7a"},"cell_type":"markdown","source":"# Make the Validation Set"},{"metadata":{"trusted":true,"_uuid":"4b6921f4e0dc22fc49b55069a58762d7a01774c3"},"cell_type":"code","source":"valid_x, valid_y = next(make_image_gen(valid_df, VALID_IMG_COUNT))\nprint(valid_x.shape, valid_y.shape)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"dd4043f60d97d8b42d3cf94c31345cccabd23025"},"cell_type":"markdown","source":"# Augment Data"},{"metadata":{"trusted":true,"_uuid":"d716a202ebd4760c4652cedfd6886d6a064b66d4"},"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\ndg_args = dict(featurewise_center = False, \n samplewise_center = False,\n rotation_range = 15, \n width_shift_range = 0.1, \n height_shift_range = 0.1, \n shear_range = 0.01,\n zoom_range = [0.9, 1.25], \n horizontal_flip = True, \n vertical_flip = True,\n fill_mode = 'reflect',\n data_format = 'channels_last')\n# brightness can be problematic since it seems to change the labels differently from the images \nif AUGMENT_BRIGHTNESS:\n dg_args[' brightness_range'] = [0.5, 1.5]\nimage_gen = ImageDataGenerator(**dg_args)\n\nif AUGMENT_BRIGHTNESS:\n dg_args.pop('brightness_range')\nlabel_gen = ImageDataGenerator(**dg_args)\n\ndef create_aug_gen(in_gen, seed = None):\n np.random.seed(seed if seed is not None else np.random.choice(range(9999)))\n for in_x, in_y in in_gen:\n seed = np.random.choice(range(9999))\n # keep the seeds syncronized otherwise the augmentation to the images is different from the masks\n g_x = image_gen.flow(255*in_x, \n batch_size = in_x.shape[0], \n seed = seed, \n shuffle=True)\n g_y = label_gen.flow(in_y, \n batch_size = in_x.shape[0], \n seed = seed, \n shuffle=True)\n\n yield next(g_x)/255.0, next(g_y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e47e7387ad8f052dbafec75522c7140b594f93a9"},"cell_type":"code","source":"cur_gen = create_aug_gen(train_gen)\nt_x, t_y = next(cur_gen)\nprint('x', t_x.shape, t_x.dtype, t_x.min(), t_x.max())\nprint('y', t_y.shape, t_y.dtype, t_y.min(), t_y.max())\n# only keep first 9 samples to examine in detail\nt_x = t_x[:9]\nt_y = t_y[:9]\nfig, (ax1, ax2) = plt.subplots(1, 2, figsize = (20, 10))\nax1.imshow(montage_rgb(t_x), cmap='gray')\nax1.set_title('images')\nax2.imshow(montage(t_y[:, :, :, 0]), cmap='gray_r')\nax2.set_title('ships')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ef3addecd90b3a516fbf38aa9a555ef8eb928198"},"cell_type":"code","source":"gc.collect()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8a4c7eee22f39c9851bccfe5756e441e7b85bf93"},"cell_type":"markdown","source":"# Model"},{"metadata":{"trusted":true,"_uuid":"95da401b3ce958d653c3bbf3ac049fe02dbe4b19"},"cell_type":"code","source":"from keras import models, layers\n# Build U-Net model\ndef upsample_conv(filters, kernel_size, strides, padding):\n return layers.Conv2DTranspose(filters, kernel_size, strides=strides, padding=padding)\ndef upsample_simple(filters, kernel_size, strides, padding):\n return layers.UpSampling2D(strides)\n\nif UPSAMPLE_MODE=='DECONV':\n upsample=upsample_conv\nelse:\n upsample=upsample_simple\n \ninput_img = layers.Input(t_x.shape[1:], name = 'RGB_Input')\npp_in_layer = input_img\nif NET_SCALING is not None:\n pp_in_layer = layers.AvgPool2D(NET_SCALING)(pp_in_layer)\n \npp_in_layer = layers.GaussianNoise(GAUSSIAN_NOISE)(pp_in_layer)\npp_in_layer = layers.BatchNormalization()(pp_in_layer)\n\nc1 = layers.Conv2D(8, (3, 3), activation='relu', padding='same') (pp_in_layer)\nc1 = layers.Conv2D(8, (3, 3), activation='relu', padding='same') (c1)\np1 = layers.MaxPooling2D((2, 2)) (c1)\n\nc2 = layers.Conv2D(16, (3, 3), activation='relu', padding='same') (p1)\nc2 = layers.Conv2D(16, (3, 3), activation='relu', padding='same') (c2)\np2 = layers.MaxPooling2D((2, 2)) (c2)\n\nc3 = layers.Conv2D(32, (3, 3), activation='relu', padding='same') (p2)\nc3 = layers.Conv2D(32, (3, 3), activation='relu', padding='same') (c3)\np3 = layers.MaxPooling2D((2, 2)) (c3)\n\nc4 = layers.Conv2D(64, (3, 3), activation='relu', padding='same') (p3)\nc4 = layers.Conv2D(64, (3, 3), activation='relu', padding='same') (c4)\np4 = layers.MaxPooling2D(pool_size=(2, 2)) (c4)\n\n\nc5 = layers.Conv2D(128, (3, 3), activation='relu', padding='same') (p4)\nc5 = layers.Conv2D(128, (3, 3), activation='relu', padding='same') (c5)\n\nu6 = upsample(64, (2, 2), strides=(2, 2), padding='same') (c5)\nu6 = layers.concatenate([u6, c4])\nc6 = layers.Conv2D(64, (3, 3), activation='relu', padding='same') (u6)\nc6 = layers.Conv2D(64, (3, 3), activation='relu', padding='same') (c6)\n\nu7 = upsample(32, (2, 2), strides=(2, 2), padding='same') (c6)\nu7 = layers.concatenate([u7, c3])\nc7 = layers.Conv2D(32, (3, 3), activation='relu', padding='same') (u7)\nc7 = layers.Conv2D(32, (3, 3), activation='relu', padding='same') (c7)\n\nu8 = upsample(16, (2, 2), strides=(2, 2), padding='same') (c7)\nu8 = layers.concatenate([u8, c2])\nc8 = layers.Conv2D(16, (3, 3), activation='relu', padding='same') (u8)\nc8 = layers.Conv2D(16, (3, 3), activation='relu', padding='same') (c8)\n\nu9 = upsample(8, (2, 2), strides=(2, 2), padding='same') (c8)\nu9 = layers.concatenate([u9, c1], axis=3)\nc9 = layers.Conv2D(8, (3, 3), activation='relu', padding='same') (u9)\nc9 = layers.Conv2D(8, (3, 3), activation='relu', padding='same') (c9)\n\nd = layers.Conv2D(1, (1, 1), activation='sigmoid') (c9)\nd = layers.Cropping2D((EDGE_CROP, EDGE_CROP))(d)\nd = layers.ZeroPadding2D((EDGE_CROP, EDGE_CROP))(d)\nif NET_SCALING is not None:\n d = layers.UpSampling2D(NET_SCALING)(d)\n\nseg_model = models.Model(inputs=[input_img], outputs=[d])\nseg_model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"9255545cdaf83c5b7bacebbd1b6a2be2b17ef6a3"},"cell_type":"code","source":"import keras.backend as K\nfrom keras.optimizers import Adam\nfrom keras.losses import binary_crossentropy\ndef dice_coef(y_true, y_pred, smooth=1):\n intersection = K.sum(y_true * y_pred, axis=[1,2,3])\n union = K.sum(y_true, axis=[1,2,3]) + K.sum(y_pred, axis=[1,2,3])\n return K.mean( (2. * intersection + smooth) / (union + smooth), axis=0)\ndef dice_p_bce(in_gt, in_pred):\n return 1e-3*binary_crossentropy(in_gt, in_pred) - dice_coef(in_gt, in_pred)\ndef true_positive_rate(y_true, y_pred):\n return K.sum(K.flatten(y_true)*K.flatten(K.round(y_pred)))/K.sum(y_true)\nseg_model.compile(optimizer=Adam(1e-4, decay=1e-6), loss=dice_p_bce, metrics=[dice_coef, 'binary_accuracy', true_positive_rate])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"179963d199018340a296980f71e65c0719784015"},"cell_type":"code","source":"from keras.callbacks import ModelCheckpoint, LearningRateScheduler, EarlyStopping, ReduceLROnPlateau\nweight_path=\"{}_weights.best.hdf5\".format('seg_model')\n\ncheckpoint = ModelCheckpoint(weight_path, monitor='val_dice_coef', verbose=1, \n save_best_only=True, mode='max', save_weights_only = True)\n\nreduceLROnPlat = ReduceLROnPlateau(monitor='val_dice_coef', factor=0.5, \n patience=3, \n verbose=1, mode='max', epsilon=0.0001, cooldown=2, min_lr=1e-6)\nearly = EarlyStopping(monitor=\"val_dice_coef\", \n mode=\"max\", \n patience=15) # probably needs to be more patient, but kaggle time is limited\ncallbacks_list = [checkpoint, early, reduceLROnPlat]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b33cbfa3e14bd0c5e4218925a86505d417d83895"},"cell_type":"code","source":"step_count = min(MAX_TRAIN_STEPS, balanced_train_df.shape[0]//BATCH_SIZE)\naug_gen = create_aug_gen(make_image_gen(balanced_train_df))\nloss_history = [seg_model.fit_generator(aug_gen, \n steps_per_epoch=step_count, \n epochs=NB_EPOCHS, \n validation_data=(valid_x, valid_y),\n callbacks=callbacks_list,\n workers=1 # the generator is not very thread safe\n )]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"3aa633fffd18ee0ed46cae8642925fd04418f87d"},"cell_type":"code","source":"def show_loss(loss_history):\n epich = np.cumsum(np.concatenate(\n [np.linspace(0.5, 1, len(mh.epoch)) for mh in loss_history]))\n fig, (ax1, ax2, ax3, ax4) = plt.subplots(1, 4, figsize=(22, 10))\n _ = ax1.plot(epich,\n np.concatenate([mh.history['loss'] for mh in loss_history]),\n 'b-',\n epich, np.concatenate(\n [mh.history['val_loss'] for mh in loss_history]), 'r-')\n ax1.legend(['Training', 'Validation'])\n ax1.set_title('Loss')\n\n _ = ax2.plot(epich, np.concatenate(\n [mh.history['true_positive_rate'] for mh in loss_history]), 'b-',\n epich, np.concatenate(\n [mh.history['val_true_positive_rate'] for mh in loss_history]),\n 'r-')\n ax2.legend(['Training', 'Validation'])\n ax2.set_title('True Positive Rate\\n(Positive Accuracy)')\n \n _ = ax3.plot(epich, np.concatenate(\n [mh.history['binary_accuracy'] for mh in loss_history]), 'b-',\n epich, np.concatenate(\n [mh.history['val_binary_accuracy'] for mh in loss_history]),\n 'r-')\n ax3.legend(['Training', 'Validation'])\n ax3.set_title('Binary Accuracy (%)')\n \n _ = ax4.plot(epich, np.concatenate(\n [mh.history['dice_coef'] for mh in loss_history]), 'b-',\n epich, np.concatenate(\n [mh.history['val_dice_coef'] for mh in loss_history]),\n 'r-')\n ax4.legend(['Training', 'Validation'])\n ax4.set_title('DICE')\n\nshow_loss(loss_history)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2e5b41a115c99ff2e779f601e8245da4e787c524"},"cell_type":"code","source":"seg_model.load_weights(weight_path)\nseg_model.save('seg_model.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"eb71d27330e2e30119e5d754645a7508d45914d8"},"cell_type":"code","source":"pred_y = seg_model.predict(valid_x)\nprint(pred_y.shape, pred_y.min(), pred_y.max(), pred_y.mean())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"809e484b90a9719c102804add8080c5ab3e1f90e"},"cell_type":"code","source":"fig, ax = plt.subplots(1, 1, figsize = (10, 10))\nax.hist(pred_y.ravel(), np.linspace(0, 1, 10))\nax.set_xlim(0, 1)\nax.set_yscale('log', nonposy='clip')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"1ff7325aa110daffcc145193d40b5cff78697e14"},"cell_type":"markdown","source":"# Prepare Full Resolution Model"},{"metadata":{"trusted":true,"_uuid":"b5ba093e4d0ee424ea6068a515529839c8b12104"},"cell_type":"code","source":"if IMG_SCALING is not None:\n fullres_model = models.Sequential()\n fullres_model.add(layers.AvgPool2D(IMG_SCALING, input_shape = (None, None, 3)))\n fullres_model.add(seg_model)\n fullres_model.add(layers.UpSampling2D(IMG_SCALING))\nelse:\n fullres_model = seg_model\nfullres_model.save('fullres_model.h5')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"ede0ee7fba00da0399325712f522a24a2585d5da"},"cell_type":"markdown","source":"# Run the test data"},{"metadata":{"trusted":true,"_uuid":"54f1e1ac7373566229680e65b58395e4a218f2ea"},"cell_type":"code","source":"test_paths = os.listdir(test_image_dir)\nprint(len(test_paths), 'test images found')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b71a5e2d208c8486674e70e1ac93ad9be3ebd975"},"cell_type":"code","source":"fig, m_axs = plt.subplots(20, 2, figsize = (10, 40))\n[c_ax.axis('off') for c_ax in m_axs.flatten()]\nfor (ax1, ax2), c_img_name in zip(m_axs, test_paths):\n c_path = os.path.join(test_image_dir, c_img_name)\n c_img = imread(c_path)\n first_img = np.expand_dims(c_img, 0)/255.0\n first_seg = fullres_model.predict(first_img)\n ax1.imshow(first_img[0])\n ax1.set_title('Image')\n ax2.imshow(first_seg[0, :, :, 0], vmin = 0, vmax = 1)\n ax2.set_title('Prediction')\nfig.savefig('test_predictions.png')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"52a8a100a3ff84745f8c806d9b3ecae1c8aef38b"},"cell_type":"markdown","source":"# Create Submission"},{"metadata":{"trusted":true,"_uuid":"3ecf9550a1ec259781dbd62f2ed4dac308e99567"},"cell_type":"code","source":"from tqdm import tqdm_notebook\nfrom skimage.morphology import binary_opening, disk\nout_pred_rows = []\nfor c_img_name in tqdm_notebook(test_paths):\n c_path = os.path.join(test_image_dir, c_img_name)\n c_img = imread(c_path)\n c_img = np.expand_dims(c_img, 0)/255.0\n cur_seg = fullres_model.predict(c_img)[0]\n cur_seg = binary_opening(cur_seg>0.5, np.expand_dims(disk(2), -1))\n cur_rles = multi_rle_encode(cur_seg)\n if len(cur_rles)>0:\n for c_rle in cur_rles:\n out_pred_rows += [{'ImageId': c_img_name, 'EncodedPixels': c_rle}]\n else:\n out_pred_rows += [{'ImageId': c_img_name, 'EncodedPixels': None}]\n gc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"bc1f3cc7cede875d71c118a5d8ecb89af18ecf83"},"cell_type":"code","source":"submission_df = pd.DataFrame(out_pred_rows)[['ImageId', 'EncodedPixels']]\nsubmission_df.to_csv('submission.csv', index=False)\nsubmission_df.sample(3)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}