{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport seaborn as sns\nimport os\nfrom sklearn.metrics import accuracy_score\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras import datasets, layers, models\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Dropout, LSTM, BatchNormalization\nfrom tensorflow.keras.callbacks import TensorBoard\nfrom tensorflow.keras.callbacks import ModelCheckpoint\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping\nfrom tensorflow.keras.callbacks import ReduceLROnPlateau\nfrom PIL import Image \nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\nfrom tensorflow.keras.layers import Conv2D , MaxPool2D , Flatten\n\nfrom tensorflow.keras.layers import Input, Lambda, Dense, Flatten\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.applications.vgg16 import VGG16\nfrom tensorflow.keras.applications.vgg16 import preprocess_input\nfrom tensorflow.keras.preprocessing import image\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator,load_img\nfrom tensorflow.keras.models import Sequential\nfrom glob import glob\nimport os, cv2, json","execution_count":null,"outputs":[]},{"metadata":{"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":"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":"train_labels.label = train_labels.label.astype('str')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMG_SIZE = 331","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_generator = ImageDataGenerator(\n                                    #featurewise_center=False,                                    \n                                    #samplewise_center=False,\n                                    #featurewise_std_normalization=False,\n                                    #samplewise_std_normalization=False, \n                                    #zca_whitening=False,\n                                    #zca_epsilon=1e-06,\n                                    rotation_range=90,\n                                    width_shift_range=0.2,\n                                    height_shift_range=0.2,\n                                    #brightness_range=None,\n                                    shear_range=25,\n                                    zoom_range=0.3,\n                                    #channel_shift_range=0.0,\n                                    #fill_mode=\"nearest\",\n                                    #cval=0.0,\n                                    horizontal_flip=True,\n                                    vertical_flip=True,\n                                    #rescale=None,\n                                    #preprocessing_function=None,\n                                    #data_format=None,\n                                    validation_split=0.2,\n                                    #dtype=None,\n) \\\n        .flow_from_dataframe(\n                            train_labels,\n                            directory = WORK_DIR + \"train_images\",\n                            x_col = \"image_id\",\n                            y_col = \"label\",\n                            #weight_col = None,\n                            target_size = (IMG_SIZE, IMG_SIZE),\n                            #color_mode = \"rgb\",\n                            #classes = 'sparse',\n                            class_mode = \"categorical\",\n                            batch_size = 10,\n                            shuffle = True,\n                            #seed = 34,\n                            #save_to_dir = None,\n                            #save_prefix = \"\",\n                            #save_format = \"png\",\n                            subset = \"training\",\n                            #interpolation = \"nearest\",\n                            #validate_filenames = True\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"valid_generator = ImageDataGenerator(\n                                    validation_split = 0.2\n) \\\n        .flow_from_dataframe(\n                            train_labels,\n                            directory = WORK_DIR + \"train_images\",\n                            x_col = \"image_id\",\n                            y_col = \"label\",\n                            target_size = (IMG_SIZE, IMG_SIZE),\n                            class_mode = \"categorical\",\n                            batch_size = 10,\n                            shuffle = True,\n                            subset = \"validation\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"BATCH_SIZE = 10\nSTEPS_PER_EPOCH = len(train_generator) / BATCH_SIZE\nVALIDATION_STEPS = len(valid_generator) / BATCH_SIZE\nEPOCHS = 500","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"valid_generator.class_indices","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.applications import NASNetLarge\nfrom keras.models import Model\ndef model_pre():\n    \n    model = models.Sequential()\n    model.add(NASNetLarge(include_top = False, weights = \"imagenet\",\n                            input_shape=(IMG_SIZE,IMG_SIZE, 3)))\n    model.add(layers.GlobalAveragePooling2D())\n    model.add(layers.Dense(5, activation = \"softmax\"))\n    \n    return model \n\nmodel = model_pre()\nmodel.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),loss='categorical_crossentropy',metrics=['accuracy'])\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learning_rate_reduction = ReduceLROnPlateau(monitor='val_accuracy',\n                                            patience=5,\n                                            verbose=1,\n                                            factor=0.25,\n                                            min_lr=0.00000003)\nes = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=20)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_check = ModelCheckpoint(\n                            \"./saved.h5\",\n                            monitor = \"val_loss\",\n                            verbose = 1,\n                            save_best_only = True,\n                            save_weights_only = False,\n                            mode = \"min\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(train_generator,steps_per_epoch = STEPS_PER_EPOCH,\n                              epochs = EPOCHS,validation_data = valid_generator,\n                              validation_steps = VALIDATION_STEPS,callbacks=[model_check,learning_rate_reduction,es])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import keras","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = keras.models.load_model(\"./saved.h5\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds = []\nsample_sub = pd.read_csv('../input/cassava-leaf-disease-classification/sample_submission.csv')\n\nfor image in sample_sub.image_id:\n    img = keras.preprocessing.image.load_img('../input/cassava-leaf-disease-classification/test_images/' + image)\n    img = keras.preprocessing.image.img_to_array(img)\n    img = keras.preprocessing.image.smart_resize(img, (331, 331))\n    img = np.expand_dims(img, 0)\n    prediction = model.predict(img)\n    preds.append(np.argmax(prediction))\n\nmy_submission = pd.DataFrame({'image_id': sample_sub.image_id, 'label': preds})\nmy_submission.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}