{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport datetime\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import accuracy_score\nimport tensorflow as tf\nfrom tensorflow.keras import models, layers\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau\nfrom tensorflow.keras.applications import EfficientNetB0\nfrom keras.optimizers import Adam\n\n# ignoring warnings\nimport warnings\nwarnings.simplefilter(\"ignore\")\n\nimport os, cv2, json\nfrom PIL import Image","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"WORK_DIR = '../input/cassava-leaf-disease-classification'\nos.listdir(WORK_DIR)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('Train images: %d' %len(os.listdir(\n    os.path.join(WORK_DIR, \"train_images\"))))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('Train images: %d' %len(os.listdir(\n    os.path.join(WORK_DIR, \"test_images\"))))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with open(os.path.join(WORK_DIR, \"label_num_to_disease_map.json\")) as file:\n    print(json.dumps(json.loads(file.read()), indent=1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_labels = pd.read_csv(os.path.join(WORK_DIR, \"train.csv\"))\ntrain_labels.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(train_labels.label, edgecolor = 'black',\n              palette = sns.color_palette(\"viridis\", 5))\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"BATCH_SIZE = 32\nSTEPS_PER_EPOCH = len(train_labels)*0.8 / BATCH_SIZE\nVALIDATION_STEPS = len(train_labels)*0.2 / BATCH_SIZE\nEPOCHS = 50\nTARGET_SIZE = 224","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_labels.label = train_labels.label.astype('str')\n\ntrain_generator = ImageDataGenerator(validation_split = 0.2,\n                                     preprocessing_function = None,\n                                     zoom_range = 0.2,\n                                     cval = 0.2,\n                                     horizontal_flip = True,\n                                     vertical_flip = True,\n                                     fill_mode = 'nearest',\n                                     shear_range = 0.2,\n                                     height_shift_range = 0.2,\n                                     width_shift_range = 0.2) \\\n    .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_generator = ImageDataGenerator(validation_split = 0.2) \\\n    .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":"def create_model():\n    model = models.Sequential()\n\n    model.add(EfficientNetB0(include_top = False, weights = 'imagenet',\n                             input_shape = (TARGET_SIZE, TARGET_SIZE, 3)))\n    \n    model.add(layers.GlobalAveragePooling2D())\n    model.add(layers.Dense(5, activation = \"softmax\"))\n\n    model.compile(optimizer = Adam(lr = 0.001),\n                  loss = \"sparse_categorical_crossentropy\",\n                  metrics = [\"acc\"])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = create_model()\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_save = ModelCheckpoint('./best_baseline_model.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 = 0.1, \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":"model.save('./baseline_model.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ss = pd.read_csv(os.path.join(WORK_DIR, \"sample_submission.csv\"))\nss","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds = []\n\nfor image_id in ss.image_id:\n    image = Image.open(os.path.join(WORK_DIR,  \"test_images\", image_id))\n    image = image.resize((TARGET_SIZE, TARGET_SIZE))\n    image = np.expand_dims(image, axis = 0)\n    preds.append(np.argmax(model.predict(image)))\n\nss['label'] = preds\nss","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ss.to_csv('submission.csv', index = False)","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}