{"cells":[{"metadata":{},"cell_type":"markdown","source":"Transfer learning from pretrained model (Resnet50) using Keras"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\nimport cv2\nimport matplotlib.pyplot as plt\nimport pandas as pd\nimport numpy as np\nimport json\nfrom keras.models import Sequential, Model\nfrom keras.layers import Dense, Flatten, Activation, Dropout, GlobalAveragePooling2D\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras import optimizers, applications\nfrom keras.callbacks import ModelCheckpoint, LearningRateScheduler, TensorBoard, EarlyStopping\nfrom keras import backend as K ","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","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":"# Example of images \nimg_names = train_df['id_code'][:10]\n\nplt.figure(figsize=[15,15])\ni = 1\nfor img_name in img_names:\n    img = cv2.imread(\"../input/aptos2019-blindness-detection/train_images/%s\" % img_name)[...,[2, 1, 0]]\n    plt.subplot(6, 5, i)\n    plt.imshow(img)\n    i += 1\nplt.show()","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 = 64\nnb_epochs = 5","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\ntrain_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_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\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 = applications.ResNet50(weights=None, \n                          include_top=False, \n                          input_shape=(img_size, img_size, 3))\nmodel.load_weights('../input/resnet50/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.trainable = False","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Adding custom layers \nx = model.output\nx = Flatten()(x)\nx = Dense(1024, activation=\"relu\")(x)\nx = Dropout(0.5)(x)\npredictions = Dense(nb_classes, activation=\"softmax\")(x)\nmodel_final = Model(input = model.input, output = predictions)\n\nmodel_final.compile(optimizers.rmsprop(lr=0.001, decay=1e-6),loss='categorical_crossentropy',metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Callbacks\n\ncheckpoint = ModelCheckpoint(\"model_1.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":"%%time\nhistory = model_final.fit_generator(generator=train_generator,                   \n                                    steps_per_epoch=100,\n                                    validation_data=valid_generator,                    \n                                    validation_steps=30,\n                                    epochs=nb_epochs,\n                                    callbacks = [checkpoint, early],\n                                    max_queue_size=16,\n                                    workers=2,\n                                    use_multiprocessing=True,\n                                    verbose=0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with open('history.json', 'w') as f:\n    json.dump(history.history, f)\n\nhistory_df = pd.DataFrame(history.history)\nhistory_df[['loss', 'val_loss']].plot()\nhistory_df[['acc', 'val_acc']].plot()","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":"%%time\ntest_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":"%%time\ntest_generator.reset()\npredict=model_final.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}