{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"collapsed":true},"cell_type":"code","source":"\nimport 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\n\nBATCH_SIZE = 16\n\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')\ntest_image_dir = os.path.join(ship_dir, 'test')\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.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)\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","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"masks = pd.read_csv(os.path.join('../input/',\n                                 'train_ship_segmentations.csv'))\nprint(masks.shape[0], 'masks found')\nprint(masks['ImageId'].value_counts().shape[0])\nmasks.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"00da4d13d5c98cc64651c4ce34bcf730a2478541"},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nunique_img_ids = masks.groupby('ImageId').size().reset_index(name='counts')\ntrain_ids, valid_ids = train_test_split(unique_img_ids, \n                 test_size = 0.3, \n                 stratify = unique_img_ids['counts'])\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":{"trusted":true,"_uuid":"8fb97bcf031a7e49e955b27d7b19db831957a41d"},"cell_type":"code","source":"train_df['counts'] = train_df.apply(lambda c_row: c_row['counts'] if \n                                    isinstance(c_row['EncodedPixels'], str) else\n                                    0, 1)\ntrain_df['counts'].hist()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"124072a5c81fdca920f036138fa34531f7a1d0ed"},"cell_type":"code","source":"train_df.groupby('counts').size()\ntrain_df['triple_boats'] = train_df['counts'].map(lambda x: (x+2)//3)\nbalanced_train_df = train_df.groupby('triple_boats').apply(lambda x: x.sample(1500))\nbalanced_train_df['counts'].hist()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true,"_uuid":"b7e23e8eddf30eb01248cd13d74c4350565714c4"},"cell_type":"code","source":"def 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)\n\ndef make_image_gen(in_df, batch_size = BATCH_SIZE):\n    all_batches = list(in_df.groupby('ImageId'))\n    out_rgb = []\n    out_mask = []\n    while True:\n        np.random.shuffle(all_batches)\n        for c_img_id, c_masks in all_batches:\n            rgb_path = os.path.join(train_image_dir, c_img_id)\n            out_rgb += [imread(rgb_path)]\n            out_mask += [masks_as_image(c_masks['EncodedPixels'].values)]\n            if len(out_rgb)>=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":"ce15d7ef875d7654612bc98a25ec568bab17abb4"},"cell_type":"code","source":"train_gen = make_image_gen(balanced_train_df)\nvalid_gen = make_image_gen(valid_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":"b9eef161ed03ba6899a6fd1847a7c7bfa4d65224"},"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":{"trusted":true,"_uuid":"fc65b3852dda4cc114f2f7b1103b5c43d50fef49"},"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                  brightness_range = [0.5, 1.5],\n                  horizontal_flip = True, \n                  vertical_flip = True,\n                  fill_mode = 'reflect',\n                   data_format = 'channels_last')\n\nimage_gen = ImageDataGenerator(**dg_args)\ndg_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":"129ffa6345f40cb19a2c94c306174a3653b985d6"},"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())\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,"collapsed":true,"_uuid":"05f04d08f33c537d84e27d319d791c0589627bd5"},"cell_type":"code","source":"EDGE_CROP = 16\nGAUSSIAN_NOISE = 0.1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"54247a766f0ed9053b6a082131197407832ac01b"},"cell_type":"code","source":"from keras import models, layers\n# Build U-Net model\n\ninput_img = layers.Input(t_x.shape[1:], name = 'RGB_Input')\npp_in_layer = layers.GaussianNoise(GAUSSIAN_NOISE)(input_img)\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 = layers.Conv2DTranspose(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 = layers.Conv2DTranspose(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 = layers.Conv2DTranspose(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 = layers.Conv2DTranspose(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)\n\nseg_model = models.Model(inputs=[input_img], outputs=[d])\nseg_model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true,"_uuid":"a71e210266e2399c3e79420c2b49c865e2068c3e"},"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 0.01*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":"060ce5d3545d2cfd239248c227a7d6303bd270b9"},"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,"collapsed":true,"_uuid":"951ee0fa6284715b34ae7ad84c570bda36475be0"},"cell_type":"code","source":"loss_history = [seg_model.fit_generator(create_aug_gen(make_image_gen(balanced_train_df)), \n                             steps_per_epoch=\n                                        min(100,\n                                            balanced_train_df.shape[0]//t_x.shape[0]), \n                             epochs=1, \n                             validation_data=valid_gen,\n                                        validation_steps = 25,\n                             callbacks=callbacks_list,\n                            workers=2)]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true,"_uuid":"913fafc34693679fb4a37fcf5827b31f34c6519d"},"cell_type":"code","source":"","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}