{"cells":[{"metadata":{},"cell_type":"markdown","source":"Import Libraries"},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install -q efficientnet","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\nimport numpy as np \nimport pandas as pd \nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport warnings\nfrom functools import partial\nwarnings.filterwarnings('ignore')\nimport json\n\nfrom sklearn import model_selection\n\nimport tensorflow as tf\nfrom tensorflow.keras.applications import Xception\nfrom tensorflow.keras.applications import InceptionV3\nimport efficientnet.tfkeras as efn\nfrom tensorflow.keras.layers import GlobalAveragePooling2D,Dense,Input,Flatten\nfrom tensorflow.keras.models import Model,Sequential\nfrom kaggle_datasets import KaggleDatasets\nimport re\nimport math\n\nimport matplotlib.pyplot as plt\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Checking the tf version\nprint(tf.__version__)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"TOP_DIR = '../input/cassava-leaf-disease-classification/'\nprint(os.listdir(TOP_DIR))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Creating Run strategy"},{"metadata":{"trusted":true},"cell_type":"code","source":"try:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver() \n    print('Running on TPU ', tpu.master())\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy() \n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Set Cloud Path"},{"metadata":{"trusted":true},"cell_type":"code","source":"GCS_DS_PATH = KaggleDatasets().get_gcs_path('cassava-leaf-disease-classification')\nGCS_DS_PATH","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Initialize the required stuffs"},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_SIZE = 600\nEPOCHS = 50\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nNUM_TRAINING_IMAGES = len(os.listdir('../input/cassava-leaf-disease-classification/train_images'))\nNUM_TEST_IMAGES = len(os.listdir('../input/cassava-leaf-disease-classification/test_images'))\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nAUTO = tf.data.experimental.AUTOTUNE","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Creating Train validation and test splits"},{"metadata":{"trusted":true},"cell_type":"code","source":"TRAINING_SAMPLE,VAL_SAMPLE = model_selection.train_test_split(tf.io.gfile.glob(GCS_DS_PATH + '/train_tfrecords/*.tfrec'),\n                                                              test_size=0.2,random_state=2021)\nTEST_SAMPLE = tf.io.gfile.glob(GCS_DS_PATH + '/test_tfrecords/*.tfrec')                                                        ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Check the size of each chunks"},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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\nNUM_TRAINING_IMAGES = count_data_items(TRAINING_SAMPLE)\nNUM_VALIDATION_IMAGES = count_data_items(VAL_SAMPLE)\nNUM_TEST_IMAGES = count_data_items(TEST_SAMPLE)\nprint('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Reading the CSV"},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.read_csv('../input/cassava-leaf-disease-classification/train.csv')\nsample_df = pd.read_csv('../input/cassava-leaf-disease-classification/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Initialize the required data pipeline"},{"metadata":{"trusted":true},"cell_type":"code","source":"def data_augment(image, label):\n    image = tf.image.random_flip_left_right(image)\n    image = tf.image.random_flip_up_down(image,)\n    image = tf.image.rot90(image, k = np.random.randint(4))\n    return image, label \n\ndef decode_image(image_data):\n    image = tf.image.decode_jpeg(image_data, channels=3)\n    image = tf.cast(image, tf.float32) / 255.0  \n    image = tf.image.resize(image, [IMAGE_SIZE, IMAGE_SIZE])\n    image = tf.reshape(image, [IMAGE_SIZE, IMAGE_SIZE, 3])\n    return image\n\ndef read_labeled_tfrecord(example):\n    LABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), \n        \"target\": tf.io.FixedLenFeature([], tf.int64),  \n    }\n    example = tf.io.parse_single_example(example, LABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    label = tf.cast(example['target'], tf.int32)\n    return image, label \n\ndef read_unlabeled_tfrecord(example):\n    UNLABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), \n        \"id\": tf.io.FixedLenFeature([], tf.string), \n    }\n    example = tf.io.parse_single_example(example, UNLABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    idnum = example['id']\n    return image, idnum\n\ndef load_dataset(filenames, labeled=True, ordered=False):\n    ignore_order = tf.data.Options()\n    if not ordered:\n        ignore_order.experimental_deterministic = False \n\n    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTO) \n    dataset = dataset.with_options(ignore_order)\n    dataset = dataset.map(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord, num_parallel_calls=AUTO)\n    return dataset\n\ndef get_training_dataset():\n    dataset = load_dataset(tf.io.gfile.glob(TRAINING_SAMPLE), labeled=True)\n    dataset = dataset.map(data_augment, num_parallel_calls=AUTO)\n    dataset = dataset.repeat() # the training dataset must repeat for several epochs\n    dataset = dataset.shuffle(2048)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO) \n    return dataset\n\ndef get_validation_dataset():\n    dataset = load_dataset(tf.io.gfile.glob(VAL_SAMPLE), labeled=True, ordered=False)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.cache()\n    dataset = dataset.prefetch(AUTO) \n    return dataset\n\ndef get_test_dataset(ordered=False):\n    dataset = load_dataset(tf.io.gfile.glob(TEST_SAMPLE), labeled=False, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO) \n    return dataset","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Creating Train and validation dataset by calling the data pipeline"},{"metadata":{"trusted":true},"cell_type":"code","source":"training_dataset = get_training_dataset()\nvalidation_dataset = get_validation_dataset()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Read json file to check the label mapping"},{"metadata":{"trusted":true},"cell_type":"code","source":"with open('../input/cassava-leaf-disease-classification/label_num_to_disease_map.json') as f:\n    labels_map=json.load(f)\n    print(labels_map)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"CLASSES = ['Cassava Bacterial Blight (CBB)','Cassava Brown Streak Disease (CBSD)','Cassava Green Mottle (CGM)',\n           'Cassava Mosaic Disease (CMD)','Healthy']","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"View Data from the folders"},{"metadata":{"trusted":true},"cell_type":"code","source":"def batch_to_numpy_images_and_labels(data):\n    images, labels = data\n    numpy_images = images.numpy()\n    numpy_labels = labels.numpy()\n    if numpy_labels.dtype == object: # binary string in this case,\n                                     # these are image ID strings\n        numpy_labels = [None for _ in enumerate(numpy_images)]\n    # If no labels, only image IDs, return None for labels (this is\n    # the case for test data)\n    return numpy_images, numpy_labels\n\ndef title_from_label_and_target(label, correct_label):\n    if correct_label is None:\n        return CLASSES[label], True\n    correct = (label == correct_label)\n    return \"{} [{}{}{}]\".format(CLASSES[label], 'OK' if correct else 'NO', u\"\\u2192\" if not correct else '',\n                                CLASSES[correct_label] if not correct else ''), correct\n\ndef display_one_flower(image, title, subplot, red=False, titlesize=1):\n    plt.subplot(*subplot)\n    plt.axis('off')\n    plt.imshow(image)\n    if len(title) > 0:\n        plt.title(title, fontsize=int(titlesize) if not red else int(titlesize/1.2), color='red' if red else 'black', fontdict={'verticalalignment':'center'})\n    return (subplot[0], subplot[1], subplot[2]+1)\n\n\ndef display_batch_of_images(databatch, predictions=None):\n    \"\"\"This will work with:\n    display_batch_of_images(images)\n    display_batch_of_images(images, predictions)\n    display_batch_of_images((images, labels))\n    display_batch_of_images((images, labels), predictions)\n    \"\"\"\n    # data\n    images, labels = batch_to_numpy_images_and_labels(databatch)\n    if labels is None:\n        labels = [None for _ in enumerate(images)]\n        \n    # auto-squaring: this will drop data that does not fit into square\n    # or square-ish rectangle\n    rows = int(math.sqrt(len(images)))\n    cols = len(images)//rows\n        \n    # size and spacing\n    FIGSIZE = 20.0\n    SPACING = 0.1\n    subplot=(rows,cols,1)\n    if rows < cols:\n        plt.figure(figsize=(FIGSIZE,FIGSIZE/cols*rows))\n    else:\n        plt.figure(figsize=(FIGSIZE/rows*cols,FIGSIZE))\n    \n    # display\n    for i, (image, label) in enumerate(zip(images[:rows*cols], labels[:rows*cols])):\n        title = '' if label is None else CLASSES[label]\n        correct = True\n        if predictions is not None:\n            title, correct = title_from_label_and_target(predictions[i], label)\n        dynamic_titlesize = FIGSIZE*SPACING/max(rows,cols)*40+3 # magic formula tested to work from 1x1 to 10x10 images\n        subplot = display_one_flower(image, title, subplot, not correct, titlesize=dynamic_titlesize)\n    \n    #layout\n    plt.tight_layout()\n    if label is None and predictions is None:\n        plt.subplots_adjust(wspace=0, hspace=0)\n    else:\n        plt.subplots_adjust(wspace=SPACING, hspace=SPACING)\n    plt.show()\n    \ndef display_training_curves(training, validation, title, subplot):\n    if subplot%10==1: # set up the subplots on the first call\n        plt.subplots(figsize=(10,10), facecolor='#F0F0F0')\n        plt.tight_layout()\n    ax = plt.subplot(subplot)\n    ax.set_facecolor('#F8F8F8')\n    ax.plot(training)\n    ax.plot(validation)\n    ax.set_title('model '+ title)\n    ax.set_ylabel(title)\n    #ax.set_ylim(0.28,1.05)\n    ax.set_xlabel('epoch')\n    ax.legend(['train', 'valid.'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ds_iter = iter(training_dataset.unbatch().batch(20))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"one_batch = next(ds_iter)\ndisplay_batch_of_images(one_batch)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"There are issues in the dataset sometime healty leafs also looks like disease "},{"metadata":{},"cell_type":"markdown","source":"Defining the call backs for training"},{"metadata":{"trusted":true},"cell_type":"code","source":"checkpoint_cb = tf.keras.callbacks.ModelCheckpoint(\n    \"EfficientNetB7.h5\",\n    save_best_only=True,\n    monitor = 'val_loss',\n    mode='min'\n)\nreduce_lr = tf.keras.callbacks.ReduceLROnPlateau(monitor = 'val_loss',\n                                  factor = 0.3,\n                                  patience = 3,\n                                  min_lr = 1e-5,\n                                  mode = 'min',\n                                  verbose = 1)\n\nearly_stopping_cb = tf.keras.callbacks.EarlyStopping(\n    monitor='val_loss',\n    mode='min', \n    patience=5,\n    restore_best_weights=True, \n    verbose=1\n)\ncallbacks = [checkpoint_cb,reduce_lr,early_stopping_cb]","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Training the model via calling the strategY"},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():    \n    pretrained_model = efn.EfficientNetB7(weights=None, include_top=False ,input_shape=[IMAGE_SIZE,IMAGE_SIZE, 3])\n    pretrained_model.trainable = False \n    \n    model = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.Dropout(0.25),\n        tf.keras.layers.Dense(1024),\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dropout(0.25),\n        tf.keras.layers.Dense(5, activation='softmax')\n    ])\n    model.add_weight('../input/keras-pretrained-models/EfficientNetB7_NoTop_ImageNet.h5')\nmodel.compile(\n    optimizer='adam',\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy']\n)\n\nhistorical = model.fit(training_dataset, \n          steps_per_epoch=STEPS_PER_EPOCH, \n          epochs=EPOCHS, \n          validation_data=validation_dataset,\n                      callbacks=callbacks)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"display_training_curves(\n    historical.history['loss'],\n    historical.history['val_loss'],\n    'loss',\n    211,\n)\ndisplay_training_curves(\n    historical.history['sparse_categorical_accuracy'],\n    historical.history['val_sparse_categorical_accuracy'],\n    'accuracy',\n    212,\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def display_confusion_matrix(cmat, score, precision, recall):\n    plt.figure(figsize=(15,15))\n    ax = plt.gca()\n    ax.matshow(cmat, cmap='Reds')\n    ax.set_xticks(range(len(CLASSES)))\n    ax.set_xticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_xticklabels(), rotation=45, ha=\"left\", rotation_mode=\"anchor\")\n    ax.set_yticks(range(len(CLASSES)))\n    ax.set_yticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_yticklabels(), rotation=45, ha=\"right\", rotation_mode=\"anchor\")\n    titlestring = \"\"\n    if score is not None:\n        titlestring += 'f1 = {:.3f} '.format(score)\n    if precision is not None:\n        titlestring += '\\nprecision = {:.3f} '.format(precision)\n    if recall is not None:\n        titlestring += '\\nrecall = {:.3f} '.format(recall)\n    if len(titlestring) > 0:\n        ax.text(101, 1, titlestring, fontdict={'fontsize': 18, 'horizontalalignment':'right', 'verticalalignment':'top', 'color':'#804040'})\n    plt.show()\n    \ndef display_training_curves(training, validation, title, subplot):\n    if subplot%10==1: # set up the subplots on the first call\n        plt.subplots(figsize=(10,10), facecolor='#F0F0F0')\n        plt.tight_layout()\n    ax = plt.subplot(subplot)\n    ax.set_facecolor('#F8F8F8')\n    ax.plot(training)\n    ax.plot(validation)\n    ax.set_title('model '+ title)\n    ax.set_ylabel(title)\n    #ax.set_ylim(0.28,1.05)\n    ax.set_xlabel('epoch')\n    ax.legend(['train', 'valid.'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cmdataset = get_validation_dataset()\nimages_ds = cmdataset.map(lambda image, label: image)\nlabels_ds = cmdataset.map(lambda image, label: label).unbatch()\n\ncm_correct_labels = next(iter(labels_ds.batch(NUM_VALIDATION_IMAGES))).numpy()\ncm_probabilities = model.predict(images_ds)\ncm_predictions = np.argmax(cm_probabilities, axis=-1)\n\nlabels = range(len(CLASSES))\ncmat = confusion_matrix(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n)\ncmat = (cmat.T / cmat.sum(axis=1)).T # normalize","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"score = f1_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\nprecision = precision_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\nrecall = recall_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\ndisplay_confusion_matrix(cmat, score, precision, recall)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dataset = get_validation_dataset()\ndataset = dataset.unbatch().batch(20)\nbatch = iter(dataset)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images, labels = next(batch)\nprobabilities = model.predict(images)\npredictions = np.argmax(probabilities, axis=-1)\ndisplay_batch_of_images((images, labels), predictions)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}