def __init__(self, config):
"""
Args:
config: config file of the current model
"""
self.config = config
# load data here
d = DataLoader(self.config)
# Get the filenames and labels
self.filenames, self.labels = d.get_sub_dataset(self.config.image_size)
# Create the Dataset using Tensorflow Data API
self.dataset = tf.data.Dataset.from_tensor_slices(self.filenames)
# Apply parse function to get the numpy array of the images
self.dataset = self.dataset.map(
map_func=self._parse_function,
num_parallel_calls=self.config.num_parallel_calls)
# Shuffle the dataset
#self.dataset = self.dataset.shuffle(self.config.buffer_size)
# Repeat the dataset indefinitely
self.dataset = self.dataset.repeat(self.config.num_epochs)
# Applying prefetch to increase the performance
# Prefetch the next 10 batches
self.dataset = self.dataset.prefetch(buffer_size=10 *
config.batch_size)
# Apply batching
self.dataset = self.dataset.batch(config.batch_size)
self.iterator = self.dataset.make_initializable_iterator()
self.image = self.iterator.get_next()
def __init__(self):
# self.config = config
# load data here
d = DataLoader("./data")
# Get the filenames and labels
self.filenames, self.labels = d.get_sub_dataset(28)
#assert len(self.filenames) == len(self.labels)
# Create the Dataset using Tensorflow Data API
self.dataset = tf.data.Dataset.from_tensor_slices(self.filenames)
# Apply parse function to get the numpy array of the images
self.dataset = self.dataset.map(self._parse_function)
# Shuffle the dataset
self.dataset = self.dataset.shuffle(self.filenames.get_shape()[0])
# Apply batching
self.dataset = self.dataset.batch(50)