def _augment_data(self, inout, nchan=6):
"""Flip, crop and rotate samples randomly."""
with tf.name_scope('data_augmentation'):
if self.fliplr:
inout = tf.image.random_flip_left_right(inout, seed=1234)
if self.flipud:
inout = tf.image.random_flip_up_down(inout, seed=3456)
if self.rotate:
angle = tf.random_uniform((), minval=0, maxval=4, dtype=tf.int32, seed=4567)
inout = tf.case([(tf.equal(angle, 1), lambda: tf.image.rot90(inout, k=1)),
(tf.equal(angle, 2), lambda: tf.image.rot90(inout, k=2)),
(tf.equal(angle, 3), lambda: tf.image.rot90(inout, k=3))],
lambda: inout)
inout.set_shape([None, None, nchan])
with tf.name_scope('crop'):
shape = tf.shape(inout)
new_height = tf.to_int32(self.output_resolution[0])
new_width = tf.to_int32(self.output_resolution[1])
height_ok = tf.assert_less_equal(new_height, shape[0])
width_ok = tf.assert_less_equal(new_width, shape[1])
with tf.control_dependencies([height_ok, width_ok]):
if self.random_crop:
inout = tf.random_crop(
inout, tf.stack([new_height, new_width, nchan]))
else:
height_offset = tf.to_int32((shape[0]-new_height)/2)
width_offset = tf.to_int32((shape[1]-new_width)/2)
inout = tf.image.crop_to_bounding_box(
inout, height_offset, width_offset,
new_height, new_width)
inout.set_shape([None, None, nchan])
inout = tf.image.resize_images(
inout, [self.output_resolution[0], self.output_resolution[1]])
fullres = inout
with tf.name_scope('resize'):
new_size = 256
inout = tf.image.resize_images(
inout, [new_size, new_size],
method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
return fullres, inout
python类case()的实例源码
def _split_and_apply_activations(self, controller_output):
""" This takes the controller output, splits it in ntm_output, read and wright adressing data.
It returns a triple of ntm_output, controller_instructions_read, controller_instructions_write.
ntm_output is a tensor, controller_instructions_read and controller_instructions_write are lists containing
the adressing instruction (k, beta, g, shift, gamma) and in case of write also the writing constructions,
consisting of an erase and an add vector.
As it is necesseary for stable results,
k and add_vector is activated via tanh, erase_vector via sigmoid (this is critical!),
shift via softmax,
gamma is sigmoided, inversed and clipped (probably not ideal)
g is sigmoided,
beta is linear (probably not ideal!) """
# splitting
ntm_output, controller_instructions_read, controller_instructions_write = tf.split(
controller_output,
np.asarray([self.output_dim,
self.read_heads * self.controller_read_head_emitting_dim,
self.write_heads * self.controller_write_head_emitting_dim]),
axis=1)
controller_instructions_read = tf.split(controller_instructions_read, self.read_heads, axis=1)
controller_instructions_write = tf.split(controller_instructions_write, self.write_heads, axis=1)
controller_instructions_read = [
tf.split(single_head_data, np.asarray([self.m_depth, 1, 1, 3, 1]), axis=1) for
single_head_data in controller_instructions_read]
controller_instructions_write = [
tf.split(single_head_data, np.asarray([self.m_depth, 1, 1, 3, 1, self.m_depth, self.m_depth]), axis=1) for
single_head_data in controller_instructions_write]
#activation
ntm_output = self.activation(ntm_output)
controller_instructions_read = [(tanh(k), hard_sigmoid(beta)+0.5, sigmoid(g), softmax(shift), 1 + 9*sigmoid(gamma)) for
(k, beta, g, shift, gamma) in controller_instructions_read]
controller_instructions_write = [
(tanh(k), hard_sigmoid(beta)+0.5, sigmoid(g), softmax(shift), 1 + 9*sigmoid(gamma), hard_sigmoid(erase_vector), tanh(add_vector)) for
(k, beta, g, shift, gamma, erase_vector, add_vector) in controller_instructions_write]
return (ntm_output, controller_instructions_read, controller_instructions_write)
