{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","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 import image\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau\nfrom tensorflow.keras.applications import EfficientNetB4\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.layers import Dense, Flatten, Dropout, Activation\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":"with open(os.path.join(WORK_DIR, \"label_num_to_disease_map.json\")) as file:\n    print(json.dumps(json.loads(file.read()), indent=4))","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.set_style(\"whitegrid\")\nfig, ax = plt.subplots(figsize = (6, 4))\n\nfor i in ['top', 'right', 'left']:\n    ax.spines[i].set_visible(False)\nax.spines['bottom'].set_color('black')\n\nsns.countplot(train_labels.label, edgecolor = 'black',\n              palette = reversed(sns.color_palette(\"viridis\", 5)))\nplt.xlabel('Classes', fontfamily = 'serif', size = 15)\nplt.ylabel('Count', fontfamily = 'serif', size = 15)\nplt.xticks(fontfamily = 'serif', size = 12)\nplt.yticks(fontfamily = 'serif', size = 12)\nax.grid(axis = 'y', linestyle = '--', alpha = 0.9)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Main parameters\nBATCH_SIZE = 8\nSTEPS_PER_EPOCH = len(train_labels)*0.8 / BATCH_SIZE\nVALIDATION_STEPS = len(train_labels)*0.2 / BATCH_SIZE\nEPOCHS = 5\nTARGET_SIZE = 512","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_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)\n\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\n\nvalidation_datagen = ImageDataGenerator(validation_split = 0.2)\n\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":"img_path = os.path.join(WORK_DIR, \"train_images\", train_labels.image_id[20])\nimg = image.load_img(img_path, target_size = (TARGET_SIZE, TARGET_SIZE))\nimg_tensor = image.img_to_array(img)\nimg_tensor = np.expand_dims(img_tensor, axis = 0)\nimg_tensor /= 255.\n\nplt.imshow(img_tensor[0])\nplt.axis('off')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"generator = train_datagen.flow_from_dataframe(train_labels.iloc[20:21],\n                         directory = os.path.join(WORK_DIR, \"train_images\"),\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\naug_images = [generator[0][0][0]/255 for i in range(10)]\nfig, axes = plt.subplots(2, 5, figsize = (20, 10))\naxes = axes.flatten()\nfor img, ax in zip(aug_images, axes):\n    ax.imshow(img)\n    ax.axis('off')\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"classes_to_predict = sorted(train_labels.label.unique())\ndropout_rate = 0.3\n\ndef create_model():\n    model = models.Sequential()\n    model.add(EfficientNetB4(include_top = False, weights = None,\n                             input_shape = (TARGET_SIZE, TARGET_SIZE, 3)))\n    model.add(layers.GlobalAveragePooling2D())\n    model.add(Dropout(dropout_rate))\n    model.add(Dense(len(classes_to_predict), activation=\"softmax\"))\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":"print('Our EfficientNet CNN has %d layers' %len(model.layers))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.load_weights('../input/cassava-leaf-keras-efficientnetb-baseline/best_baseline_model.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_save = ModelCheckpoint('./EffNetB4_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(\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":"avg_acc = sum(history.history['acc'])/len(history.history['acc'])\navg_val_acc = sum(history.history['val_acc'])/len(history.history['val_acc'])\navg_loss = sum(history.history['loss'])/len(history.history['loss'])\navg_val_loss = sum(history.history['val_loss'])/len(history.history['val_loss'])\n\nprint('Training produced an average accuracy of %.3f and average loss of %.3f' % (avg_acc,avg_loss))\nprint('Validation produced an average accuracy of %.3f and average loss of %.3f' % (avg_val_acc,avg_val_loss))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"acc = 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":"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}