def call(self, inputs):
if self.data_format == 'channels_last':
out = ktf.pad(inputs, [[0, 0]] + self.paddings + [[0, 0]],
mode='REFLECT')
else:
out = ktf.pad(inputs, [[0, 0], [0, 0]] + self.paddings,
mode='REFLECT')
return out
def _find_subpixel_maxima(x,
kernel_size,
sigma,
upsample_factor,
coordinate_scale=1,
confidence_scale=255.):
kernel = gaussian_kernel_2d(kernel_size, sigma)
kernel = tf.expand_dims(kernel, 0)
x_shape = tf.shape(x)
rows = x_shape[1]
cols = x_shape[2]
max_vals = tf.reduce_max(tf.reshape(x, [-1, rows * cols]), axis=1)
max_vals = tf.reshape(max_vals, [-1, 1]) / confidence_scale
row_pad = rows // 2 - kernel_size // 2
col_pad = cols // 2 - kernel_size // 2
padding = [[0, 0], [row_pad, row_pad - 1], [col_pad, col_pad - 1]]
kernel = tf.pad(kernel, padding)
row_center = row_pad + (kernel_size // 2)
col_center = col_pad + (kernel_size // 2)
center = tf.stack([row_center, col_center])
center = tf.expand_dims(center, 0)
center = tf.cast(center, dtype=tf.float32)
shifts = _upsampled_registration(x, kernel, upsample_factor)
shifts = center - shifts
shifts *= coordinate_scale
maxima = tf.concat([shifts[:, ::-1], max_vals], -1)
return maxima
def nn_loss(self, reference, target, neighborhood_size=(3, 3)):
v_pad = neighborhood_size[0] // 2
h_pad = neighborhood_size[1] // 2
val_pad = ktf.pad(reference,
[[0, 0], [v_pad, v_pad], [h_pad, h_pad], [0, 0]],
mode='CONSTANT',
constant_values=-10000)
reference_tensors = []
for i_begin in range(0, neighborhood_size[0]):
i_end = i_begin - neighborhood_size[0] + 1
i_end = None if i_end == 0 else i_end
for j_begin in range(0, neighborhood_size[1]):
j_end = j_begin - neighborhood_size[0] + 1
j_end = None if j_end == 0 else j_end
sub_tensor = val_pad[:, i_begin:i_end, j_begin:j_end, :]
reference_tensors.append(ktf.expand_dims(sub_tensor, -1))
reference = ktf.concat(reference_tensors, axis=-1)
target = ktf.expand_dims(target, axis=-1)
abs = ktf.abs(reference - target)
norms = ktf.reduce_sum(abs, reduction_indices=[-2])
loss = ktf.reduce_min(norms, reduction_indices=[-1])
return loss
