himanshurawlani

class TuneReporter(tf.keras.callbacks.Callback):
    """Tune Callback for Keras."""

    def __init__(self, reporter=None, freq="epoch", logs=None):
        """Initializer.
        Args:
            freq (str): Sets the frequency of reporting intermediate results.
        """
        self.iteration = 0
        logs = logs or {}

himanshurawlani

class Trainable:
    def __init__(self, train_dir, val_dir, snapshot_dir, final_run=False):
        # Initializing state variables for the run
        self.train_dir = train_dir
        self.val_dir = val_dir
        self.final_run = final_run
        self.snapshot_dir = snapshot_dir

    def train(self, config, reporter=None):
        # If you get out of memory error try reducing the maximum batch size

himanshurawlani

logger.info("Initializing ray")
ray.init(configure_logging=False)

logger.info("Initializing ray search space")
search_space, intial_best_config = create_search_space()

logger.info("Initializing scheduler and search algorithms")
# Use HyperBand scheduler to earlystop unpromising runs
scheduler = AsyncHyperBandScheduler(time_attr='training_iteration',
					metric="val_loss",

himanshurawlani

{
	"lr": hp.choice("lr", [0.0001, 0.001, 0.01, 0.1]),
	"batch_size": hp.choice("batch_size", [8, 16, 32, 64]), 
	"use_contrast": hp.choice("use_contrast", ["True", "False"]),
	"contrast_factor": hp.choice("contrast_factor", [0.1, 0.2, 0.3, 0.4]),
	"use_rotation": hp.choice("use_rotation", ["True", "False"]),
	"rotation_factor": hp.choice("rotation_factor", [0.1, 0.2, 0.3, 0.4]),
	"use_flip": hp.choice("use_flip", ["True", "False"]),
	"flip_mode": hp.choice("flip_mode", ["horizontal", "vertical"]),
	"dropout_rate": hp.choice("dropout_rate", [0.1, 0.2, 0.3, 0.4, 0.5]),

himanshurawlani

{
	"lr": 0.001,
	"batch_size": 16, 
	"use_contrast": "True",
	"contrast_factor": 0.2,
	"use_rotation": "True",
	"rotation_factor": 0.2,
	"use_flip": "True",
	"flip_mode": "horizontal",
	"dropout_rate": 0.2,

himanshurawlani

def augment_images(x, config):
    if config['use_contrast'] == "True":
        x = tf.keras.layers.experimental.preprocessing.RandomContrast(
            config['contrast_factor']
        )(x)

    if config['use_rotation'] == "True":
        x = tf.keras.layers.experimental.preprocessing.RandomRotation(
            config['rotation_factor']
        )(x)

himanshurawlani

def FCN_model(config, len_classes=5):
    
    input = tf.keras.layers.Input(shape=(None, None, 3))

    # Adding data augmentation layers
    x = augment_images(input, config)

    # You can create a fixed number of convolutional blocks or 
    # You can also use a loop if number of layers is also a hyperparameter
    x = tf.keras.layers.Conv2D(filters=config['conv_block1_filters'], kernel_size=3, strides=1)(x)

himanshurawlani

def make_serving_request(image_batch):
    data = json.dumps({"signature_name": "serving_default",
                       "instances": image_batch.tolist()})

    headers = {"content-type": "application/json"}

    os.environ['NO_PROXY'] = 'localhost'
    json_response = requests.post(
        'http://localhost:8501/v1/models/flower_classifier:predict', data=data, headers=headers)

himanshurawlani

def export(input_h5_file, export_path):
    # The export path contains the name and the version of the model
    tf.keras.backend.set_learning_phase(0)  # Ignore dropout at inference
    model = tf.keras.models.load_model(input_h5_file)
    model.save(export_path, save_format='tf')
    print(f"SavedModel created at {export_path}")
    

himanshurawlani

def train(model, train_generator, val_generator, epochs = 50):
    model.compile(optimizer=tf.keras.optimizers.Adam(lr=0.0001),
                    loss='categorical_crossentropy',
                    metrics=['accuracy'])

    checkpoint_path = './snapshots'
    os.makedirs(checkpoint_path, exist_ok=True)
    model_path = os.path.join(checkpoint_path, 'model_epoch_{epoch:02d}_loss_{loss:.2f}_acc_{acc:.2f}_val_loss_{val_loss:.2f}_val_acc_{val_acc:.2f}.h5')
    
    history = model.fit_generator(generator=train_generator,