{"cells":[{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport os\nimport keras\nimport matplotlib.pyplot as plt\nfrom keras.layers import Dense,GlobalAveragePooling2D\nfrom keras.applications import ResNet50\nfrom keras.preprocessing import image\nfrom keras.applications.mobilenet import preprocess_input\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Model\nfrom keras.optimizers import Adam\nfrom keras.callbacks import Callback,ModelCheckpoint, LearningRateScheduler, TensorBoard, EarlyStopping\nfrom sklearn.metrics import cohen_kappa_score\nfrom keras.models import model_from_json\nimport cv2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"base_model=ResNet50(weights='../input/resnet-50-weights-file/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',include_top=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x=base_model.output\n\n\nx=GlobalAveragePooling2D()(x)\nx=Dense(1024,activation='relu')(x) #we add dense layers so that the model can learn more complex functions and classify for better results.\nx=Dense(512,activation='relu')(x) #dense layer 3\nx=Dense(128,activation='relu')(x) #dense layer 3\nx=Dense(64,activation='relu')(x) #dense layer 3\nx=Dense(32,activation='relu')(x) #dense layer 3\npreds=Dense(5,activation='softmax')(x) #final layer with softmax activation","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model=Model(inputs=base_model.input,outputs=preds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# for layer in model.layers[:30]:\n#     layer.trainable=False\n# for layer in model.layers[30:]:\n#     layer.trainable=True\n\nfor layer in model.layers:\n    layer.trainable = True","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.read_csv('../input/aptos2019-blindness-detection/train.csv')\ntrain_df[\"id_code\"]=train_df[\"id_code\"].apply(lambda x:x+\".png\")\ntrain_df['diagnosis'] = train_df['diagnosis'].astype(str)\ntrain_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"nb_classes = 5\nlbls = list(map(str, range(nb_classes)))\nbatch_size = 32\nimg_size = 224\nnb_epochs = 15","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# train_datagen=ImageDataGenerator(\n#     rescale=1./255, \n#     validation_split=0.25,\n#     horizontal_flip = True,    \n#     zoom_range = 0.3,\n#     width_shift_range = 0.3,\n#     height_shift_range=0.3\n#     )\n\ntrain_datagen=ImageDataGenerator(\n    rescale=1./255,\n    zca_whitening=True,\n    rotation_range=45,\n    width_shift_range=0.2, \n    height_shift_range=0.2,\n    horizontal_flip=True,\n    vertical_flip=True,\n    validation_split=0.1,   \n    zoom_range = 0.3,\n    )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_generator=train_datagen.flow_from_dataframe(\n    dataframe=train_df,\n    directory=\"../input/aptos2019-blindness-detection/train_images\",\n    x_col=\"id_code\",\n    y_col=\"diagnosis\",\n    batch_size=batch_size,\n    shuffle=True,\n    class_mode=\"categorical\",\n    classes=lbls,\n    target_size=(img_size,img_size),\n    subset='training')\n\nprint('break')\n\nvalid_generator=train_datagen.flow_from_dataframe(\n    dataframe=train_df,\n    directory=\"../input/aptos2019-blindness-detection/train_images\",\n    x_col=\"id_code\",\n    y_col=\"diagnosis\",\n    batch_size=batch_size,\n    shuffle=True,\n    class_mode=\"categorical\", \n    classes=lbls,\n    target_size=(img_size,img_size),\n    subset='validation')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer=Adam(lr=0.00005),loss='categorical_crossentropy',metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Callbacks\n\ncheckpoint = ModelCheckpoint(\"model.h5\", monitor='val_loss', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)\nearly = EarlyStopping(monitor='val_loss', min_delta=0, patience=5, verbose=1, mode='auto')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Configure the TensorBoard callback and fit your model\n\n# tensorboard_callback = TensorBoard(\"logs\")\n\n# model.fit_generator(generator=train_generator,\n#                     steps_per_epoch=30,\n#                     validation_data=valid_generator,                    \n#                     validation_steps=30,\n#                     epochs=nb_epochs,\n#                     callbacks=[tensorboard_callback])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"checkpoint = ModelCheckpoint(\n    'resnet50_model.h5', \n    monitor='val_loss', \n    verbose=0, \n    save_best_only=True, \n    save_weights_only=False,\n    mode='auto'\n)\n\nmodel.compile(optimizer=Adam(lr=0.00005),loss='categorical_crossentropy',metrics=['accuracy'])\n\nhistory = model.fit_generator(\n    generator=train_generator,\n    steps_per_epoch=30,\n    epochs=15,\n    validation_data=valid_generator,\n    validation_steps = 30,\n    callbacks=[checkpoint])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer=Adam(lr=0.00001),loss='categorical_crossentropy',metrics=['accuracy'])\n\nhistory = model.fit_generator(\n    generator=train_generator,\n    steps_per_epoch=30,\n    epochs=10,\n    validation_data=valid_generator,\n    validation_steps = 30,\n    callbacks=[checkpoint])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer=Adam(lr=0.000005),loss='categorical_crossentropy',metrics=['accuracy'])\n\nhistory = model.fit_generator(\n    generator=train_generator,\n    steps_per_epoch=30,\n    epochs=5,\n    validation_data=valid_generator,\n    validation_steps = 30,\n    callbacks=[checkpoint])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_json = model.to_json()\nwith open(\"model_resnet.json\", \"w\") as json_file:\n    json_file.write(model_json)\nmodel.save_weights(\"model_resnet50.h5\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sam_sub_df = pd.read_csv('../input/aptos2019-blindness-detection/sample_submission.csv')\nsam_sub_df[\"id_code\"]=sam_sub_df[\"id_code\"].apply(lambda x:x+\".png\")\nprint(sam_sub_df.shape)\nsam_sub_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_datagen = ImageDataGenerator(rescale=1./255)\ntest_generator = test_datagen.flow_from_dataframe(  \n        dataframe=sam_sub_df,\n        directory = \"../input/aptos2019-blindness-detection/test_images\",    \n        x_col=\"id_code\",\n        target_size = (img_size,img_size),\n        batch_size = 1,\n        shuffle = False,\n        class_mode = None\n        )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict=model.predict_generator(test_generator, steps = len(test_generator.filenames))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"filenames=test_generator.filenames\nresults=pd.DataFrame({\"id_code\":filenames,\n                      \"diagnosis\":np.argmax(predict,axis=1)})\nresults['id_code'] = results['id_code'].map(lambda x: str(x)[:-4])\nresults.to_csv(\"submission.csv\",index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results.head()","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}