{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt\nimport tensorflow as tf\nimport seaborn as sns\nimport cv2\nimport tqdm\nimport keras\nimport keras\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.preprocessing.image import load_img\nfrom keras.preprocessing.image import array_to_img\nfrom keras.preprocessing.image import img_to_array\nfrom keras.applications.resnet50 import ResNet50\nfrom keras.applications.resnet50 import preprocess_input\nfrom keras.models import Model\nfrom keras.models import Sequential\nfrom keras.layers.convolutional import Conv2D\nfrom keras.layers.convolutional import MaxPooling2D\nfrom keras.layers.pooling import GlobalAveragePooling2D\nfrom keras.layers import Input\nfrom keras.layers.core import Dropout\nfrom keras.layers.core import Flatten\nfrom keras.layers.core import Dense\nfrom keras.callbacks import ModelCheckpoint\nfrom keras.callbacks import ReduceLROnPlateau\nfrom keras.callbacks import EarlyStopping\nfrom keras.layers.normalization import BatchNormalization\nfrom keras.activations import softmax\nfrom keras.activations import elu\nfrom keras.activations import relu\nfrom keras.optimizers import Adam\nfrom keras.optimizers import RMSprop\nfrom keras.optimizers import SGD\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_df = pd.read_csv('../input/aptos2019-blindness-detection/train.csv')\ntest_df = pd.read_csv('../input/aptos2019-blindness-detection/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.hist(train_df['diagnosis'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"rows = 3\ncolumns = 4\nfig = plt.figure(figsize=(4*rows, 5*columns))\nfor i in range(columns*rows):\n        image_path = train_df['id_code']\n        image_path = image_path[i]\n        image_id = train_df['diagnosis']\n        image_id = image_id[i]\n        img = cv2.imread(f'../input/aptos2019-blindness-detection/train_images/{image_path}.png')\n        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n        new_img = cv2.resize(img, (224, 224))\n        fig.add_subplot(rows, columns, i+1)\n        plt.title(image_id)\n        plt.imshow(new_img)\n        plt.tight_layout()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"rows = 3\ncolumns = 4\nfig = plt.figure(figsize=(4*rows, 5*columns))\nfor i in range(columns*rows):\n        image_path_test = test_df['id_code']\n        image_id_test = image_path_test[i]\n        img_test = cv2.imread(f'../input/aptos2019-blindness-detection/test_images/{image_id_test}.png')\n        img_test = cv2.cvtColor(img_test, cv2.COLOR_BGR2RGB)\n        img_test = cv2.resize(img_test, (224, 224))\n        fig.add_subplot(rows, columns, i+1)\n        plt.title(image_id_test)\n        plt.imshow(img_test)\n        plt.tight_layout()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.id_code = train_df.id_code.apply(lambda x: x + \".png\")\ntest_df.id_code = test_df.id_code.apply(lambda x: x + \".png\")\ntrain_df['diagnosis'] = train_df['diagnosis'].astype('str')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datagen = ImageDataGenerator(rescale=1. / 255, \n                                         validation_split=0.15, \n                                         horizontal_flip=True,\n                                         vertical_flip=True, \n                                         rotation_range=40, \n                                         zoom_range=0.2, \n                                         shear_range=0.1,\n                                        fill_mode='nearest')\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"imgPath = f\"../input/aptos2019-blindness-detection/train_images/cd54d022e37d.png\"\nimg = load_img(imgPath)\ndata = img_to_array(img)\nsamples = np.expand_dims(data, 0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_generator = train_datagen.flow_from_dataframe(dataframe=train_df,\n                                                    directory=\"../input/aptos2019-blindness-detection/train_images/\",\n                                                    x_col=\"id_code\",\n                                                    y_col=\"diagnosis\",\n                                                    batch_size=12,\n                                                    class_mode=\"categorical\",\n                                                    target_size=(224, 224),\n                                                    subset='training',\n                                                    shaffle=True,\n                                                    seed=12,\n                                                    )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"valid_generator = train_datagen.flow_from_dataframe(dataframe=train_df,\n                                                    directory=\"../input/aptos2019-blindness-detection/train_images/\",\n                                                    x_col=\"id_code\",\n                                                    y_col=\"diagnosis\",\n                                                    batch_size = 12,\n                                                    class_mode=\"categorical\",\n                                                    target_size=(224, 224),\n                                                    subset='validation',\n                                                    shaffle=True,\n                                                    seed=12\n                                                    )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def create_resnet(img_dim, CHANNEL, n_class):\n    input_tensor = Input(shape=(img_dim, img_dim, CHANNEL))\n    base_model = ResNet50(weights = 'imagenet', include_top = False, input_tensor = input_tensor)\n    base_model.load_weights('../input/resnet50/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5', by_name=True)\n    x = GlobalAveragePooling2D()(base_model.output)\n    x = BatchNormalization()(x)\n    x = Dropout(0.4)(x)\n    x = Dense(2048, activation = elu)(x)\n    x = BatchNormalization()(x)\n    x = Dropout(0.4)(x)\n    x = Dense(1024, activation = elu)(x)\n    x = BatchNormalization()(x)\n    x = Dropout(0.3)(x)\n    x = Dense(512, activation = elu)(x)\n    x = BatchNormalization()(x)\n    x = Dropout(0.5)(x)\n    output_layer = Dense(n_class, activation = 'softmax', name = 'Output_layer')(x)\n    model_resnet = Model(input_tensor, output_layer)\n    \n    return model_resnet\n\nNUM_CLASSES = train_df['diagnosis'].nunique()\nIMG_DIM = 224\nCHANNEL_SIZE = 3\nmodel_resnet = create_resnet(IMG_DIM, CHANNEL_SIZE, NUM_CLASSES)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_resnet.compile(\n    optimizer = keras.optimizers.SGD(lr = 1e-3,decay=1e-6, momentum=0.9, nesterov=True), \n    loss = keras.losses.categorical_crossentropy,\n    metrics = ['accuracy']\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"BATCH_SIZE = 12\nNUM_EPOCHS = 60\nNUB_TRAIN_STEPS = train_generator.n // train_generator.batch_size\nNUB_VALID_STEPS = valid_generator.n // valid_generator.batch_size\n\neraly_stop = EarlyStopping(monitor='val_loss', min_delta=0.0001, patience=3, verbose=1, mode='auto')\nreduce_lr = ReduceLROnPlateau(monitor='val_loss', min_delta=0.0004, patience=2, factor=0.1, min_lr=1e-6, mode='auto',\n                              verbose=1)\nNUB_TRAIN_STEPS, NUB_VALID_STEPS\nmodel_resnet.fit_generator(\n    generator = train_generator,\n    steps_per_epoch = NUB_TRAIN_STEPS,\n    validation_data = valid_generator,\n    validation_steps = NUB_VALID_STEPS,\n    epochs = NUM_EPOCHS,\n    callbacks = [eraly_stop, reduce_lr],\n    verbose = 2\n)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}