{"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 cv2\nimport os \nimport numpy as np \nfrom random import shuffle \nfrom tqdm import tqdm \nimport matplotlib.pyplot as plt\nfrom tensorflow.keras.preprocessing import image\nimport math \nimport datetime\nimport time\nimport random\nimport gc  \nimport json\nfrom sklearn.metrics import accuracy_score\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\nimport tensorflow as tf\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Dropout , Activation, Flatten,Conv2D,MaxPooling2D\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras import optimizers\nfrom tensorflow.keras import applications \nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sess = tf.compat.v1.Session(config=tf.compat.v1.ConfigProto(log_device_placement=True))\ntf.compat.v1.keras.backend.set_session(sess)\n#from tensorflow.python.client import device_lib\n#print(device_lib.list_local_devices())\nprint(\"Num GPUs Available: \", len(tf.config.experimental.list_physical_devices('GPU')))\n\ntrain_dir=\"../input/cassava-leaf-disease-classification/train_images\"\ntest_dir=\"../input/cassava-leaf-disease-classification/test_images\"\ntrain_csv=pd.read_csv('../input/cassava-leaf-disease-classification/train.csv')\ndf_test=pd.read_csv('../input/cassava-leaf-disease-classification/sample_submission.csv')\ntrain_csv.describe()\nprint(train_csv.head())\n\nfilenames = ['../input/cassava-leaf-disease-classification/train_images/' + fname for fname in train_csv['image_id'].tolist()]\n#train_csv.label=train.label.astype(str)\nlabels = train_csv['label'].tolist()\n\ntrain_filenames, val_filenames, train_labels, val_labels = train_test_split(filenames,\n                                                                            labels,\n                                                                            train_size=0.9,\n                                                                            random_state=420)\n\nnum_train = len(train_filenames)\nnum_val = len(val_filenames)\n\n#print(len(train_labels))\n#from IPython.display import Image, display\n#display(Image(train_filenames[653]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_SIZE = 128\n\n\ndef _parse_fn(filename, label):\n  image_string = tf.io.read_file(filename)\n  \n  image_decoded = tf.image.decode_jpeg(image_string)\n  image_normalized = (tf.cast(image_decoded, tf.float32)/127.5) - 1\n  image_resized = tf.image.resize(image_normalized, (IMAGE_SIZE, IMAGE_SIZE))\n  return image_resized, label","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"BATCH_SIZE = 32\n\ntrain_data = tf.data.Dataset.from_tensor_slices((tf.constant(train_filenames), tf.constant(train_labels))).map(_parse_fn).shuffle(buffer_size=10000).batch(BATCH_SIZE)\n\n\nval_data = tf.data.Dataset.from_tensor_slices((tf.constant(val_filenames), tf.constant(val_labels))).map(_parse_fn).batch(BATCH_SIZE)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMG_SHAPE = (IMAGE_SIZE, IMAGE_SIZE, 3)\n\nbase_model = tf.keras.applications.MobileNetV2(input_shape=IMG_SHAPE,\n                                               include_top=False, \n                                               weights='imagenet')\nbase_model.trainable = False","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\n\nmodel = keras.Sequential()\nmodel.add(keras.layers.Flatten(input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)))\nmodel.add(keras.layers.Dense(128, activation='relu'))\nmodel.add(keras.layers.Dense(5, activation = 'softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#MODEL 2\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\n\nmodel2 = keras.Sequential()\nmodel2.add(keras.layers.Conv2D(32, kernel_size = (3, 3), activation='relu', input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)))\nmodel2.add(keras.layers.MaxPooling2D(pool_size=(2,2)))\nmodel2.add(keras.layers.BatchNormalization())\nmodel2.add(keras.layers.Conv2D(64, kernel_size=(3,3), activation='relu'))\nmodel2.add(keras.layers.MaxPooling2D(pool_size=(2,2)))\nmodel2.add(keras.layers.BatchNormalization())\nmodel2.add(keras.layers.Conv2D(64, kernel_size=(3,3), activation='relu'))\nmodel2.add(keras.layers.MaxPooling2D(pool_size=(2,2)))\nmodel2.add(keras.layers.BatchNormalization())\nmodel2.add(keras.layers.Conv2D(96, kernel_size=(3,3), activation='relu'))\nmodel2.add(keras.layers.MaxPooling2D(pool_size=(2,2)))\nmodel2.add(keras.layers.BatchNormalization())\nmodel2.add(keras.layers.Conv2D(32, kernel_size=(3,3), activation='relu'))\nmodel2.add(keras.layers.MaxPooling2D(pool_size=(2,2)))\nmodel2.add(keras.layers.BatchNormalization())\nmodel2.add(keras.layers.Dropout(0.2))\nmodel2.add(keras.layers.Flatten())\nmodel2.add(keras.layers.Dense(128, activation='relu'))\nmodel2.add(keras.layers.Dropout(0.3))\nmodel2.add(keras.layers.Dense(5, activation = 'softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learning_rate = 0.0001\n\n\nmodel2.compile(optimizer=tf.keras.optimizers.Adam(lr=learning_rate),\n             loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n             metrics=['accuracy'])\n\nmodel2.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#TRAIN\nnum_epochs = 30\nsteps_per_epoch = round(num_train)//BATCH_SIZE\nval_steps = 20\n\nhistory = model2.fit(train_data.repeat(),\n                    epochs=num_epochs,\n                    steps_per_epoch = steps_per_epoch,\n                    validation_data=val_data.repeat(), \n                    validation_steps=val_steps)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_loss, test_acc = model2.evaluate(val_data, verbose=2)\nprint('\\nTest accuracy:', test_acc)","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}