{"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":"markdown","source":"# Set some parameters","metadata":{}},{"cell_type":"code","source":"import tensorflow as tf\nfrom kaggle_datasets import KaggleDatasets\nimport numpy as np\n!gsutil ls $GCS_DS_PATH","metadata":{"execution":{"iopub.status.busy":"2022-01-09T14:32:09.203035Z","iopub.execute_input":"2022-01-09T14:32:09.20345Z","iopub.status.idle":"2022-01-09T14:33:32.904695Z","shell.execute_reply.started":"2022-01-09T14:32:09.20341Z","shell.execute_reply":"2022-01-09T14:33:32.903607Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMAGE_SIZE = [192, 192] # at this size, a GPU will run out of memory. Use the TPU\nEPOCHS = 5\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nNUM_TRAINING_IMAGES = 12753\nNUM_TEST_IMAGES = 7382\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE","metadata":{"execution":{"iopub.status.busy":"2022-01-09T14:26:12.359064Z","iopub.execute_input":"2022-01-09T14:26:12.35939Z","iopub.status.idle":"2022-01-09T14:26:12.364305Z","shell.execute_reply.started":"2022-01-09T14:26:12.359362Z","shell.execute_reply":"2022-01-09T14:26:12.363407Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load my data\n\nThis data is loaded from Kaggle and automatically sharded to maximize parallelization.","metadata":{}},{"cell_type":"code","source":"import glob\ndef decode_image(image_data):\n    image = tf.image.decode_jpeg(image_data, channels=3)\n    image = tf.cast(image, tf.float32) / 255.0  # convert image to floats in [0, 1] range\n    image = tf.reshape(image, [*IMAGE_SIZE, 3]) # explicit size needed for TPU\n    return image\n\ndef read_labeled_tfrecord(example):\n    LABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        \"class\": tf.io.FixedLenFeature([], tf.int64),  # shape [] means single element\n    }\n    example = tf.io.parse_single_example(example, LABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    label = tf.cast(example['class'], tf.int32)\n    return image, label # returns a dataset of (image, label) pairs\n\ndef read_unlabeled_tfrecord(example):\n    UNLABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        \"id\": tf.io.FixedLenFeature([], tf.string),  # shape [] means single element\n        # class is missing, this competitions's challenge is to predict flower classes for the test dataset\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 # returns a dataset of image(s)\n\ndef load_dataset(filenames, labeled=True, ordered=False):\n    # Read from TFRecords. For optimal performance, reading from multiple files at once and\n    # disregarding data order. Order does not matter since we will be shuffling the data anyway.\n\n    ignore_order = tf.data.Options()\n    if not ordered:\n        ignore_order.experimental_deterministic = False # disable order, increase speed\n\n    dataset = tf.data.TFRecordDataset(filenames) # 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(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord)\n    # returns a dataset of (image, label) pairs if labeled=True or (image, id) pairs if labeled=False\n    return dataset\n\ndef get_training_dataset():\n    dataset = load_dataset(tf.io.gfile.glob(GCS_DS_PATH + '/tfrecords-jpeg-192x192/train/*.tfrec'), labeled=True)\n    dataset = dataset.repeat() # the training dataset must repeat for several epochs\n    dataset = dataset.shuffle(2048)\n    dataset = dataset.batch(BATCH_SIZE)\n    return dataset\n\ndef get_validation_dataset():\n    dataset = load_dataset(tf.io.gfile.glob(GCS_DS_PATH + '/tfrecords-jpeg-192x192/val/*.tfrec'), labeled=True, ordered=False)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.cache()\n    return dataset\n\ndef get_test_dataset(ordered=False):\n    dataset = load_dataset(tf.io.gfile.glob(GCS_DS_PATH + '/tfrecords-jpeg-192x192/test/*.tfrec'), labeled=False, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    return dataset\n\nprint(glob.glob(\"*\"))","metadata":{"execution":{"iopub.status.busy":"2022-01-09T14:30:10.312581Z","iopub.execute_input":"2022-01-09T14:30:10.313081Z","iopub.status.idle":"2022-01-09T14:30:10.330203Z","shell.execute_reply.started":"2022-01-09T14:30:10.313047Z","shell.execute_reply":"2022-01-09T14:30:10.329096Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Build a model on TPU (or GPU, or CPU...) with Tensorflow 2.1!","metadata":{}},{"cell_type":"code","source":"with strategy.scope():    \n    pretrained_model = tf.keras.applications.VGG16(weights='imagenet', include_top=False ,input_shape=[*IMAGE_SIZE, 3])\n    pretrained_model.trainable = False # tramsfer learning\n    \n    model = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(104, activation='softmax')\n    ])\n        \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)","metadata":{"execution":{"iopub.status.busy":"2022-01-09T14:24:35.689507Z","iopub.status.idle":"2022-01-09T14:24:35.689902Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Compute your predictions on the test set!\n\nThis will create a file that can be submitted to the competition.","metadata":{}},{"cell_type":"code","source":"test_ds = get_test_dataset(ordered=True) # since we are splitting the dataset and iterating separately on images and ids, order matters.\n\nprint('Computing predictions...')\ntest_images_ds = test_ds.map(lambda image, idnum: image)\nprobabilities = model.predict(test_images_ds)\npredictions = np.argmax(probabilities, axis=-1)\nprint(predictions)\n\nprint('Generating submission.csv file...')\ntest_ids_ds = test_ds.map(lambda image, idnum: idnum).unbatch()\ntest_ids = next(iter(test_ids_ds.batch(NUM_TEST_IMAGES))).numpy().astype('U') # all in one batch\nnp.savetxt('submission.csv', np.rec.fromarrays([test_ids, predictions]), fmt=['%s', '%d'], delimiter=',', header='id,label', comments='')","metadata":{"execution":{"iopub.status.busy":"2022-01-09T14:24:35.690672Z","iopub.status.idle":"2022-01-09T14:24:35.691048Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}