{"cells":[{"metadata":{"_uuid":"5e0c8a1e-8bd8-4943-b684-44ac9cdc6620","_cell_guid":"786eeb32-4ef5-4c81-9c87-cd079077ce2e","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\n#for 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":"!pip install --quiet /kaggle/input/kerasapplications\n!pip install --quiet /kaggle/input/efficientnet-git","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"aeec83f6-c83a-43f9-8f11-55a573f7836c","_cell_guid":"6e283b85-2177-4105-bc80-ecf576db7083","trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport json\n\nfrom PIL import Image\nimport cv2\nimport seaborn as sb\n\n# Seb 06-01-21\nimport tensorflow as tf\nfrom tensorflow import keras\nimport json\nimport math, re, os\nfrom math import sqrt\n\nfrom kaggle_datasets import KaggleDatasets\nfrom matplotlib import pyplot as plt\nfrom sklearn.model_selection import train_test_split\nfrom functools import partial\n\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"402dc299-bcdc-45d5-b8bb-48c371c3744b","_cell_guid":"23d70849-1551-4380-b452-949319af17cf","trusted":true},"cell_type":"code","source":"\n\nprint(\"Tensorflow version \" + tf.__version__)\nprint(\"Keras version \" + keras.__version__)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Detect TPU\ntry:\n tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n print('Device:', tpu.master())\n tf.config.experimental_connect_to_cluster(tpu)\n tf.tpu.experimental.initialize_tpu_system(tpu)\n strategy = tf.distribute.experimental.TPUStrategy(tpu)\nexcept:\n strategy = tf.distribute.get_strategy()\nprint('Number of replicas:', strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# set up variables\nAUTOTUNE = tf.data.experimental.AUTOTUNE\nGCS_PATH = KaggleDatasets().get_gcs_path('cassava-leaf-disease-classification')\n# GCS_PATH2 = KaggleDatasets().get_gcs_path('cassava-recreate-stratificated-tfrecords')\n\nGCS_NewTFPure512 = KaggleDatasets().get_gcs_path('cassava-leaf-disease-tfrecords-512x512')\n# GCS_NewTFCenter512 = KaggleDatasets().get_gcs_path('cassava-leaf-disease-tfrecords-center-512x512')\n# GCS_NewTFExternal512 = KaggleDatasets().get_gcs_path('cassava-leaf-disease-tfrecords-external-512x512')\n \nIMAGE_SIZE = [512,512]\nCLASSES = ['0', '1', '2', '3', '4']\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Load the data\n# split the data\n#Because our data consists of training and test images only, we're going to split our training data into training and validation data using the train_test_split() function.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Decode the data\n#turn the images into tensors\n#normalize the image (get every pixel to have a value between 0 and 1)\ndef decode_image(image):\n image = tf.image.decode_jpeg(image, channels=3)\n image = tf.cast(image, tf.float32) / 255.0\n image = tf.reshape(image, [*IMAGE_SIZE, 3])\n return image","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#setting up variables X and y; in this case image and prediction (for images with no label)\ndef read_tfrecord(example, labeled):\n tfrecord_format = {\n \"image\": tf.io.FixedLenFeature([], tf.string),\n \"target\": tf.io.FixedLenFeature([], tf.int64)\n } if labeled else {\n \"image\": tf.io.FixedLenFeature([], tf.string),\n \"image_name\": tf.io.FixedLenFeature([], tf.string)\n }\n example = tf.io.parse_single_example(example, tfrecord_format)\n image = decode_image(example['image'])\n if labeled:\n label = tf.cast(example['target'], tf.int32)\n return image, label\n idnum = example['image_name']\n return image, idnum","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# the following code will load the dataset using the TPU\ndef load_dataset(filenames, labeled=True, ordered=False):\n ignore_order = tf.data.Options()\n if not ordered:\n ignore_order.experimental_deterministic = False # disable order, increase speed\n dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTOTUNE) # automatically interleaves reads from multiple files\n dataset = dataset.with_options(ignore_order) # uses data as soon as it streams in, rather than in its original order\n dataset = dataset.map(partial(read_tfrecord, labeled=labeled), num_parallel_calls=AUTOTUNE)\n return dataset","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"TEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test_tfrecords/ld_test*.tfrec')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from __future__ import absolute_import\nfrom __future__ import division\nfrom __future__ import print_function\n\nimport inspect\nimport math\nimport tensorflow.compat.v1 as tf\n\n\n\n# This signifies the max integer that the controller RNN could predict for the\n# augmentation scheme.\n_MAX_LEVEL = 10.\n\ndef policy_v0():\n \"\"\"Autoaugment policy that was used in AutoAugment Paper.\"\"\"\n # Each tuple is an augmentation operation of the form\n # (operation, probability, magnitude). Each element in policy is a\n # sub-policy that will be applied sequentially on the image.\n policy = [\n [('Equalize', 0.8, 1), ('ShearY', 0.8, 4)],\n [('Color', 0.4, 9), ('Equalize', 0.6, 3)],\n [('Color', 0.4, 1), ('Rotate', 0.6, 8)],\n [('Solarize', 0.8, 3), ('Equalize', 0.4, 7)],\n [('Solarize', 0.4, 2), ('Solarize', 0.6, 2)],\n [('Color', 0.2, 0), ('Equalize', 0.8, 8)],\n [('Equalize', 0.4, 8), ('SolarizeAdd', 0.8, 3)],\n [('ShearX', 0.2, 9), ('Rotate', 0.6, 8)],\n [('Color', 0.6, 1), ('Equalize', 1.0, 2)],\n [('Invert', 0.4, 9), ('Rotate', 0.6, 0)],\n [('Equalize', 1.0, 9), ('ShearY', 0.6, 3)],\n [('Color', 0.4, 7), ('Equalize', 0.6, 0)],\n [('Posterize', 0.4, 6), ('AutoContrast', 0.4, 7)],\n [('Solarize', 0.6, 8), ('Color', 0.6, 9)],\n [('Solarize', 0.2, 4), ('Rotate', 0.8, 9)],\n [('Rotate', 1.0, 7), ('TranslateY', 0.8, 9)],\n [('ShearX', 0.0, 0), ('Solarize', 0.8, 4)],\n [('ShearY', 0.8, 0), ('Color', 0.6, 4)],\n [('Color', 1.0, 0), ('Rotate', 0.6, 2)],\n [('Equalize', 0.8, 4), ('Equalize', 0.0, 8)],\n [('Equalize', 1.0, 4), ('AutoContrast', 0.6, 2)],\n [('ShearY', 0.4, 7), ('SolarizeAdd', 0.6, 7)],\n [('Posterize', 0.8, 2), ('Solarize', 0.6, 10)],\n [('Solarize', 0.6, 8), ('Equalize', 0.6, 1)],\n [('Color', 0.8, 6), ('Rotate', 0.4, 5)],\n ]\n return policy\n\n\ndef policy_vtest():\n \"\"\"Autoaugment test policy for debugging.\"\"\"\n # Each tuple is an augmentation operation of the form\n # (operation, probability, magnitude). Each element in policy is a\n # sub-policy that will be applied sequentially on the image.\n policy = [\n [('TranslateX', 1.0, 4), ('Equalize', 1.0, 10)],\n ]\n return policy\n\n\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Cross Validation"},{"metadata":{},"cell_type":"markdown","source":"Pure 512x512"},{"metadata":{"trusted":true},"cell_type":"code","source":"GCS_NewTFCenter512 = KaggleDatasets().get_gcs_path('cassava-leaf-disease-tfrecords-center-512x512')\n\nTRAINING_FILENAMES_1, VALID_FILENAMES_1 = train_test_split(\n tf.io.gfile.glob(GCS_NewTFCenter512 + '/Id_train*.tfrec'),\n test_size=0.2, random_state=1\n )\n\n\nTRAINING_FILENAMES_2, VALID_FILENAMES_2 = train_test_split(\n tf.io.gfile.glob(GCS_NewTFCenter512 + '/Id_train*.tfrec'),\n test_size=0.2, random_state=2\n )\n\n\nTRAINING_FILENAMES_3, VALID_FILENAMES_3 = train_test_split(\n tf.io.gfile.glob(GCS_NewTFCenter512 + '/Id_train*.tfrec'),\n test_size=0.2, random_state=100\n )\n\n\nTRAINING_FILENAMES_4, VALID_FILENAMES_4 = train_test_split(\n tf.io.gfile.glob(GCS_NewTFCenter512 + '/Id_train*.tfrec'),\n test_size=0.2, random_state=103\n )\n\n\nTRAINING_FILENAMES_5, VALID_FILENAMES_5 = train_test_split(\n tf.io.gfile.glob(GCS_NewTFCenter512 + '/Id_train*.tfrec'),\n test_size=0.2, random_state=108\n )\n\nVALID_FILENAMES_1, VALID_FILENAMES_2, VALID_FILENAMES_3, VALID_FILENAMES_4, VALID_FILENAMES_5","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"512x512 center"},{"metadata":{"trusted":true},"cell_type":"code","source":"#TRAINING_FILENAMES_1, VALID_FILENAMES_1 = train_test_split(\n# tf.io.gfile.glob(GCS_NewTFPure512 + '/Id_train*.tfrec'),\n# test_size=0.2, random_state=1\n# )\n\n#TRAINING_FILENAMES_2, VALID_FILENAMES_2 = train_test_split(\n# tf.io.gfile.glob(GCS_NewTFPure512 + '/Id_train*.tfrec'),\n# test_size=0.2, random_state=2\n# )\n\n#TRAINING_FILENAMES_3, VALID_FILENAMES_3 = train_test_split(\n# tf.io.gfile.glob(GCS_NewTFPure512 + '/Id_train*.tfrec'),\n# test_size=0.2, random_state=100\n# )\n\n#TRAINING_FILENAMES_4, VALID_FILENAMES_4 = train_test_split(\n# tf.io.gfile.glob(GCS_NewTFPure512 + '/Id_train*.tfrec'),\n# test_size=0.2, random_state=103\n# )\n\n#TRAINING_FILENAMES_5, VALID_FILENAMES_5 = train_test_split(\n# tf.io.gfile.glob(GCS_NewTFPure512 + '/Id_train*.tfrec'),\n# test_size=0.2, random_state=108\n# )\n\n#VALID_FILENAMES_1, VALID_FILENAMES_2, VALID_FILENAMES_3, VALID_FILENAMES_4, VALID_FILENAMES_5","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"512x512 external\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"#not working\n#GCS_NewTFExternal512 = KaggleDatasets().get_gcs_path('cassava-leaf-disease-tfrecords-external-512x512')\n\n#TRAINING_FILENAMES_1, VALID_FILENAMES_1 = train_test_split(\n# tf.io.gfile.glob(GCS_NewTFExternal512 + '/C*.tfrec'),\n# test_size=0.2, random_state=1\n# )\n\n\n\n#TRAINING_FILENAMES_2, VALID_FILENAMES_2 = train_test_split(\n# tf.io.gfile.glob(GCS_NewTFExternal512 + '/C*.tfrec'),\n# test_size=0.2, random_state=2\n# )\n\n\n#TRAINING_FILENAMES_3, VALID_FILENAMES_3 = train_test_split(\n# tf.io.gfile.glob(GCS_NewTFExternal512 + '/C*.tfrec'),\n# test_size=0.2, random_state=100\n# )\n\n\n#TRAINING_FILENAMES_4, VALID_FILENAMES_4 = train_test_split(\n # tf.io.gfile.glob(GCS_NewTFExternal512 + '/C*.tfrec'),\n # test_size=0.2, random_state=103\n# )\n\n\n# TRAINING_FILENAMES_5, VALID_FILENAMES_5 = train_test_split(\n# tf.io.gfile.glob(GCS_NewTFExternal512 + '/C*.tfrec'),\n# test_size=0.2, random_state=108\n# )\n\n#VALID_FILENAMES_1, VALID_FILENAMES_2, VALID_FILENAMES_3, VALID_FILENAMES_4, VALID_FILENAMES_5","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#The following functions will be used to load our training, validation, and test datasets, as well as print out the number of images in each dataset.\ndef get_training_dataset():\n dataset = load_dataset(TRAINING_FILENAMES, labeled=True) \n dataset = dataset.map(data_augment, num_parallel_calls=AUTOTUNE) \n dataset = dataset.repeat()\n dataset = dataset.shuffle(2048)\n dataset = dataset.batch(BATCH_SIZE)\n dataset = dataset.prefetch(AUTOTUNE)\n return dataset\n\n\ndef get_validation_dataset(ordered=False):\n dataset = load_dataset(VALID_FILENAMES, labeled=True, ordered=ordered) \n dataset = dataset.batch(BATCH_SIZE)\n dataset = dataset.cache()\n dataset = dataset.prefetch(AUTOTUNE)\n return dataset\n\n\n\ndef get_test_dataset(ordered=False):\n dataset = load_dataset(TEST_FILENAMES, labeled=False, ordered=ordered)\n dataset = dataset.batch(BATCH_SIZE)\n dataset = dataset.prefetch(AUTOTUNE)\n return dataset\n\n\ndef count_data_items(filenames):\n n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in filenames]\n return np.sum(n)\n\n\n\nNUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES_1)\nNUM_VALIDATION_IMAGES = count_data_items(VALID_FILENAMES_1)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\n\nprint('Dataset: {} training images, {} validation images, {} (unlabeled) test images'.format(\n NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n#adding in augmentations\ndef data_augment(image, label):\n # Thanks to the dataset.prefetch(AUTO) statement in the following function this happens essentially for free on TPU. \n # Data pipeline code is executed on the \"CPU\" part of the TPU while the TPU itself is computing gradients.\n# image = tf.image.random_flip_left_right(image)\n# image = tf.image.random_contrast(image)\n# image = tf.image.random_jpeg_quality(image)\n return image, label","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#build model\nlr_scheduler = keras.optimizers.schedules.ExponentialDecay(\n initial_learning_rate=1e-2, \n decay_steps=10000, \n decay_rate=0.90)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"BATCH_SIZE = 16 * strategy.num_replicas_in_sync\nEPOCHS = 2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import efficientnet.keras as efn\n\n#model\nwith strategy.scope(): \n# img_adjust_layer = tf.keras.layers.Lambda(tf.keras.applications.efficientnet.preprocess_input, input_shape=[*IMAGE_SIZE, 3])\n \n #base_model = efn.EfficientNetB3(weights='imagenet')\n model = efn.EfficientNetB3(weights='imagenet')\n# base_model.trainable = False\n \n# model = tf.keras.Sequential([\n# tf.keras.layers.BatchNormalization(renorm=True),\n# img_adjust_layer,\n# base_model,\n# tf.keras.layers.GlobalAveragePooling2D(),\n# # tf.keras.layers.GlobalMaxPooling2D(),\n# # tf.keras.layers.Dropout(0.2),\n# tf.keras.layers.Dense(8, activation='relu'),\n# tf.keras.layers.Dense(len(CLASSES), activation='softmax') \n# ])\n\n\n model.compile(\n optimizer=tf.keras.optimizers.Adam(learning_rate=lr_scheduler, epsilon=0.001),\n loss='sparse_categorical_crossentropy', \n metrics=['sparse_categorical_accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# load data\nTRAINING_FILENAMES=TRAINING_FILENAMES_1\nVALID_FILENAMES=VALID_FILENAMES_1\ntrain_dataset_1 = get_training_dataset()\nvalid_dataset_1 = get_validation_dataset()\n\nTRAINING_FILENAMES=TRAINING_FILENAMES_2\nVALID_FILENAMES=VALID_FILENAMES_2\ntrain_dataset_2 = get_training_dataset()\nvalid_dataset_2 = get_validation_dataset()\n\nTRAINING_FILENAMES=TRAINING_FILENAMES_3\nVALID_FILENAMES=VALID_FILENAMES_3\ntrain_dataset_3 = get_training_dataset()\nvalid_dataset_3 = get_validation_dataset()\n\nTRAINING_FILENAMES=TRAINING_FILENAMES_4\nVALID_FILENAMES=VALID_FILENAMES_4\ntrain_dataset_4 = get_training_dataset()\nvalid_dataset_4 = get_validation_dataset()\n\nTRAINING_FILENAMES=TRAINING_FILENAMES_5\nVALID_FILENAMES=VALID_FILENAMES_5\ntrain_dataset_5 = get_training_dataset()\nvalid_dataset_5 = get_validation_dataset()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = train_dataset_1\nvalid_dataset = valid_dataset_1\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_2\nvalid_dataset = valid_dataset_2\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_3\nvalid_dataset = valid_dataset_3\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_4\nvalid_dataset = valid_dataset_4\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_5\nvalid_dataset = valid_dataset_5\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = train_dataset_1\nvalid_dataset = valid_dataset_1\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_2\nvalid_dataset = valid_dataset_2\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_3\nvalid_dataset = valid_dataset_3\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_4\nvalid_dataset = valid_dataset_4\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_5\nvalid_dataset = valid_dataset_5\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = train_dataset_1\nvalid_dataset = valid_dataset_1\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_2\nvalid_dataset = valid_dataset_2\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_3\nvalid_dataset = valid_dataset_3\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_4\nvalid_dataset = valid_dataset_4\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_5\nvalid_dataset = valid_dataset_5\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = train_dataset_1\nvalid_dataset = valid_dataset_1\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_2\nvalid_dataset = valid_dataset_2\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_3\nvalid_dataset = valid_dataset_3\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_4\nvalid_dataset = valid_dataset_4\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_5\nvalid_dataset = valid_dataset_5\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = train_dataset_1\nvalid_dataset = valid_dataset_1\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_2\nvalid_dataset = valid_dataset_2\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_3\nvalid_dataset = valid_dataset_3\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_4\nvalid_dataset = valid_dataset_4\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_5\nvalid_dataset = valid_dataset_5\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = train_dataset_1\nvalid_dataset = valid_dataset_1\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_2\nvalid_dataset = valid_dataset_2\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_3\nvalid_dataset = valid_dataset_3\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_4\nvalid_dataset = valid_dataset_4\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)\n\ntrain_dataset = train_dataset_5\nvalid_dataset = valid_dataset_5\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_dataset, \n steps_per_epoch=STEPS_PER_EPOCH, \n epochs=EPOCHS,\n validation_data=valid_dataset,\n validation_steps=VALID_STEPS)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Because we're using a pre-trained model, we expect there to be a large number of non-trainable parameters (because the weights have already been assigned in the pre-trained model).\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Evaluating our model\n# print out variables available to us\nprint(history.history.keys())\n\n\n# create learning curves to evaluate model performance\nhistory_frame = pd.DataFrame(history.history)\nhistory_frame.loc[:, ['loss', 'val_loss']].plot()\nhistory_frame.loc[:, ['sparse_categorical_accuracy', 'val_sparse_categorical_accuracy']].plot();","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.save('model.h5')","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}