def batch_inputs(paths,
reference_shape,
batch_size=32,
is_training=False,
num_landmarks=68,
mirror_image=False):
"""Reads the files off the disk and produces batches.
Args:
paths: a list of directories that contain training images and
the corresponding landmark files.
reference_shape: a numpy array [num_landmarks, 2]
batch_size: the batch size.
is_traininig: whether in training mode.
num_landmarks: the number of landmarks in the training images.
mirror_image: mirrors the image and landmarks horizontally.
Returns:
images: a tf tensor of shape [batch_size, width, height, 3].
lms: a tf tensor of shape [batch_size, 68, 2].
lms_init: a tf tensor of shape [batch_size, 68, 2].
"""
files = tf.concat([
list(map(str, sorted(Path(d).parent.glob(Path(d).name))))
for d in paths
], 0)
filename_queue = tf.train.string_input_producer(files,
shuffle=is_training,
capacity=1000)
filename = filename_queue.dequeue()
image, lms, lms_init = tf.py_func(
partial(load_image, is_training=is_training,
mirror_image=mirror_image),
[filename, reference_shape], # input arguments
[tf.float32, tf.float32, tf.float32], # output types
name='load_image')
# The image has always 3 channels.
image.set_shape([None, None, 3])
if is_training:
image = distort_color(image)
lms = tf.reshape(lms, [num_landmarks, 2])
lms_init = tf.reshape(lms_init, [num_landmarks, 2])
images, lms, inits, shapes = tf.train.batch(
[image, lms, lms_init, tf.shape(image)],
batch_size=batch_size,
num_threads=4 if is_training else 1,
capacity=1000,
enqueue_many=False,
dynamic_pad=True)
return images, lms, inits, shapes
def batch_inputs(paths,
reference_shape,
batch_size=32,
is_training=False,
num_landmarks=68,
mirror_image=False):
"""Reads the files off the disk and produces batches.
Args:
paths: a list of directories that contain training images and
the corresponding landmark files.
reference_shape: a numpy array [num_landmarks, 2]
batch_size: the batch size.
is_traininig: whether in training mode.
num_landmarks: the number of landmarks in the training images.
mirror_image: mirrors the image and landmarks horizontally.
Returns:
images: a tf tensor of shape [batch_size, width, height, 3].
lms: a tf tensor of shape [batch_size, 68, 2].
lms_init: a tf tensor of shape [batch_size, 68, 2].
"""
files = tf.concat(0, [map(str, sorted(Path(d).parent.glob(Path(d).name)))
for d in paths])
filename_queue = tf.train.string_input_producer(files,
shuffle=is_training,
capacity=1000)
filename = filename_queue.dequeue()
image, lms, lms_init = tf.py_func(
partial(load_image, is_training=is_training,
mirror_image=mirror_image),
[filename, reference_shape], # input arguments
[tf.float32, tf.float32, tf.float32], # output types
name='load_image'
)
# The image has always 3 channels.
image.set_shape([None, None, 3])
if is_training:
image = distort_color(image)
lms = tf.reshape(lms, [num_landmarks, 2])
lms_init = tf.reshape(lms_init, [num_landmarks, 2])
images, lms, inits, shapes = tf.train.batch(
[image, lms, lms_init, tf.shape(image)],
batch_size=batch_size,
num_threads=4 if is_training else 1,
capacity=1000,
enqueue_many=False,
dynamic_pad=True)
return images, lms, inits, shapes