{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"# loading packages\n\nimport os\nimport pandas as pd\nfrom tensorflow.keras import layers, models\nfrom tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.applications import EfficientNetB0\nimport matplotlib.pyplot as plt\nimport seaborn as sns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# work dir\n\nWORK_DIR = '../input/cassava-leaf-disease-classification'\ntrain_labels = pd.read_csv(os.path.join(WORK_DIR, \"train.csv\"))\n\n# main parameters\n\nBATCH_SIZE = 8\nSTEPS_PER_EPOCH = len(train_labels) * 0.8 / BATCH_SIZE\nVALIDATION_STEPS = len(train_labels) * 0.2 / BATCH_SIZE\nEPOCHS = 20\nTARGET_SIZE = 512","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# data\n\ntrain_labels.label = train_labels.label.astype('str')\n\ntrain_datagen = ImageDataGenerator(validation_split=0.2,\n                                   preprocessing_function=None,\n                                   rotation_range=45,\n                                   zoom_range=0.2,\n                                   horizontal_flip=True,\n                                   vertical_flip=True,\n                                   fill_mode='nearest',\n                                   shear_range=0.1,\n                                   height_shift_range=0.1,\n                                   width_shift_range=0.1)\ntrain_generator = train_datagen.flow_from_dataframe(train_labels,\n                                                    directory=os.path.join(WORK_DIR, \"train_images\"),\n                                                    subset=\"training\",\n                                                    x_col=\"image_id\",\n                                                    y_col=\"label\",\n                                                    target_size=(TARGET_SIZE, TARGET_SIZE),\n                                                    batch_size=BATCH_SIZE,\n                                                    class_mode=\"sparse\")\n\nvalidation_datagen = ImageDataGenerator(validation_split=0.2)\nvalidation_generator = validation_datagen.flow_from_dataframe(train_labels,\n                                                              directory=os.path.join(WORK_DIR, \"train_images\"),\n                                                              subset=\"validation\",\n                                                              x_col=\"image_id\",\n                                                              y_col=\"label\",\n                                                              target_size=(TARGET_SIZE, TARGET_SIZE),\n                                                              batch_size=BATCH_SIZE,\n                                                              class_mode=\"sparse\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# modeling\n\ndef create_model():\n    model = models.Sequential()\n    model.add(EfficientNetB0(include_top=False, weights='imagenet', input_shape=(TARGET_SIZE, TARGET_SIZE, 3)))\n    model.add(layers.GlobalAveragePooling2D())\n    model.add(layers.Dense(5, activation='softmax'))\n    \n    model.compile(optimizer=Adam(lr=0.001), loss=\"sparse_categorical_crossentropy\", metrics=[\"acc\"])\n    return model\n\n\nmodel = create_model()\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true},"cell_type":"code","source":"# training\n\nmodel_save = ModelCheckpoint('./best_weights.h5', \n                             save_best_only = True, \n                             save_weights_only = True,\n                             monitor = 'val_loss', \n                             mode = 'min', verbose = 1)\nearly_stop = EarlyStopping(monitor = 'val_loss', min_delta = 0.001, \n                           patience = 5, mode = 'min', verbose = 1,\n                           restore_best_weights = True)\nreduce_lr = ReduceLROnPlateau(monitor = 'val_loss', factor = 0.3, \n                              patience = 2, min_delta = 0.001, \n                              mode = 'min', verbose = 1)\n\n\nhistory = model.fit_generator(\n    train_generator,\n    steps_per_epoch = STEPS_PER_EPOCH,\n    epochs = EPOCHS,\n    validation_data = validation_generator,\n    validation_steps = VALIDATION_STEPS,\n    callbacks = [model_save, early_stop, reduce_lr]\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# plot\n\nacc = history.history['acc']\nval_acc = history.history['val_acc']\nloss = history.history['loss']\nval_loss = history.history['val_loss']\n\nepochs = range(1, len(acc) + 1)\n\nfig, (ax1, ax2) = plt.subplots(1, 2, figsize=(15, 5))\nsns.set_style(\"white\")\nplt.suptitle('Train history', size = 15)\n\nax1.plot(epochs, acc, \"bo\", label = \"Training acc\")\nax1.plot(epochs, val_acc, \"b\", label = \"Validation acc\")\nax1.set_title(\"Training and validation acc\")\nax1.legend()\n\nax2.plot(epochs, loss, \"bo\", label = \"Training loss\", color = 'red')\nax2.plot(epochs, val_loss, \"b\", label = \"Validation loss\", color = 'red')\nax2.set_title(\"Training and validation loss\")\nax2.legend()\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.save('./model.h5')\nwith open('./model.json', 'w') as outfile:\n    outfile.write(model.to_json())","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}