{"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_minor":4,"nbformat":4,"cells":[{"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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import glob\nimport shutil\nimport json\nimport itertools\nimport seaborn as sns\nfrom PIL import Image\nfrom collections import Counter\nimport tensorflow as tf\nimport keras\nimport matplotlib.pyplot as plt\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import GlobalAveragePooling2D, Flatten, Dense, Dropout, BatchNormalization\nfrom tensorflow.keras.optimizers import RMSprop, Adam, SGD\nfrom tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"work_dir = '../input/cassava-leaf-disease-classification/'\nos.listdir(work_dir)\ntrain_path = '/kaggle/input/cassava-leaf-disease-classification/train_images/'","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = pd.read_csv(work_dir + 'train.csv')\n# data.head()\nprint(Counter(data['label']))\n# print(len(data))21397","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data['label'].hist()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"f = open(work_dir + 'label_num_to_disease_map.json')\nreal_labels = json.load(f)\nreal_labels = {int(k):v for k, v in real_labels.items()}\n\ndata['class_name'] = data.label.map(real_labels)\nprint(data.head())","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data['class_name'].unique()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def showImages(images):\n    random_images = [np.random.choice(images) for i in range(100)]\n    \n    #Adjust size of image\n    plt.figure(figsize = (10, 10))\n    \n    \n    for i in range(5):\n        plt.subplot(4, 4, i+1)\n        img = plt.imread(train_path + random_images[i])\n        plt.imshow(img, cmap = 'gray')\n        plt.axis('off')\n        \n    plt.tight_layout()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"classCBB = data[data['label'] == 0]\nclassCBSD = data[data['label'] == 1]\nclassCGM = data[data['label'] == 2]\nclassCMD = data[data['label'] == 3]\nclassHealthy=data[data['label']==4]","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Cassava Bacterial Blight Disease\nclassCBB=data[data['label']==0]\nshowImages(classCBB['image_id'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Cassava Brown Streak Disease\nclassCBSD=data[data['label']==1]\nshowImages(classCBSD['image_id'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Cassava Green Mottle Disease\nclassCGM=data[data['label']==2]\nshowImages(classCGM['image_id'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Cassava Mosaic Disease\nclassCMD=data[data['label']==3]\nshowImages(classCMD['image_id'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Healthy plant images\nshowImages(classHealthy['image_id'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class0 = classCBB.sample(frac = 0.99)\nclass1 = classCBSD.sample(frac = 0.9)\nclass2 = classCGM.sample(frac = 0.9)\nclass3 = classCMD.sample(frac = 0.9)\nclass4 = classHealthy.sample(frac = 0.9)\n\nframes = [class0, class1, class2, class3, class4]\nfinalData = pd.concat(frames)\n# finalData.head()\nlen(finalData)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\ntrain, val = train_test_split(finalData, test_size = 0.05, random_state = 37, stratify = finalData['class_name'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\n\nimg_size = 227\nsize = (img_size, img_size)\nn_class = 5\n\ndatapen = ImageDataGenerator(\n                            rotation_range = 60,\n                            width_shift_range = 0.2,\n                            height_shift_range = 0.2,\n                            shear_range = 0.2,\n                            zoom_range = 0.2,\n                            horizontal_flip = True,\n                            vertical_flip = True,\n                            fill_mode = 'nearest'\n                            )\n\ntrain_set = datapen.flow_from_dataframe(train,\n                                       directory = train_path,\n                                       seed = 7,\n                                       x_col = 'image_id',\n                                       y_col = 'class_name',\n                                       target_size = size,\n                                       class_mode = 'categorical',\n                                       interpolation = 'nearest',\n                                       shuffle = True,\n                                       batch_size = 32)\n\nval_set = datapen.flow_from_dataframe(val,\n                                       directory = train_path,\n                                       seed = 7,\n                                       x_col = 'image_id',\n                                       y_col = 'class_name',\n                                       target_size = size,\n                                       class_mode = 'categorical',\n                                       interpolation = 'nearest',\n                                       shuffle = True,\n                                       batch_size = 32)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def create_model():\n    model = keras.models.Sequential([\n    keras.layers.Conv2D(filters=96, kernel_size=(11,11), strides=(4,4), activation='relu', input_shape=(227,227,3)),\n    keras.layers.BatchNormalization(),\n    keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n        \n    keras.layers.Conv2D(filters=256, kernel_size=(5,5), strides=(1,1), activation='relu', padding=\"same\"),\n    keras.layers.BatchNormalization(),\n    keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n        \n    keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n    keras.layers.BatchNormalization(),\n        \n    keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n    keras.layers.BatchNormalization(),\n        \n    keras.layers.Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n    keras.layers.BatchNormalization(),\n        \n    keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n    keras.layers.Flatten(),\n    keras.layers.Dense(4096, activation='relu'),\n    keras.layers.BatchNormalization(),\n    keras.layers.Dropout(0.4),\n    keras.layers.Dense(4096, activation='relu'),\n    keras.layers.BatchNormalization(),\n    keras.layers.Dropout(0.4),\n    keras.layers.Dense(5, activation='softmax')\n    ])\n    \n    return model","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = create_model()\nmodel.summary()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"epoch = 30\nstep_size_train = train_set.n//train_set.batch_size\nstep_size_valid = val_set.n//val_set.batch_size","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(loss='sparse_categorical_crossentropy', optimizer=tf.optimizers.SGD(lr=0.001), metrics=['accuracy'])\nmodel.summary()\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":" def model_fit():\n    leaf_model = create_model()\n    \n    \n    loss = tf.keras.losses.CategoricalCrossentropy(from_logits = False,\n                                                   label_smoothing = 0.001,\n                                                   name = 'categorical_crossentropy')\n    \n    leaf_model.compile(optimizer = Adam(learning_rate = 2e-5),\n                      loss = loss,\n                      metrics = ['categorical_accuracy'])\n    \n    es = EarlyStopping(monitor = 'val_loss', mode = 'min', patience = 5, restore_best_weights = True, verbose = 1)\n    \n    \n    checkpoint_cb = ModelCheckpoint('Cassava_model',\n                                   save_best_only = True,\n                                   monitor = 'val_loss',\n                                   mode = 'min')\n    \n    reduce_lr = ReduceLROnPlateau(monitor = 'val_loss',\n                                 factor = 0.3,\n                                 patience = 3,\n                                 min_lr = 1e-6,\n                                 mode = 'min',\n                                 verbose = 1)\n    \n    history = leaf_model.fit(train_set,\n                            validation_data = val_set,\n                            epochs = epoch,\n                            steps_per_epoch = step_size_train,\n                            validation_steps = step_size_valid,\n                            callbacks = [es, checkpoint_cb, reduce_lr])\n    \n    \n    leaf_model.save('Cassava_model_alexnet.h5')\n    \n    return history","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = model_fit()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"acc = history.history['categorical_accuracy']\nval_acc = history.history['val_categorical_accuracy']\n\nloss = history.history['loss']\nval_loss = history.history['val_loss']\n\nepochs_range = range(epoch)\n\nplt.figure(figsize = (8, 8))\nplt.subplot(1, 2, 1)\nplt.plot(epochs_range, acc, label = 'Training accuracy')\nplt.plot(epochs_range, val_acc, label = 'Validation accuracy')\nplt.legend(loc = 'lower right')\nplt.title('Training and Validation Accuracy')\n\nplt.subplot(1, 2, 2)\nplt.plot(epochs_range, loss, label = 'Training loss')\nplt.plot(epochs_range, val_loss, label = 'Validation loss')\nplt.legend(loc = 'upper right')\nplt.title('Training and Validation Loss')\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n    \n    ","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}