def call(self, inputs):
"""
inputs [batch, seq, windows_size, 1, filters ]
"""
values = inputs[:, :(self.seq - 1), :, :, :]
query = inputs[:, (self.seq - 1), :, :, :]
values = tf.reshape(values,
[-1, self.windows_size, 1, self.filters_in])
values_out = K.conv2d(
values,
self.weight_value,
strides=(1, 1),
padding='valid',
data_format="channels_last"
) # [ batch*(seq-1) , rest_window, 1, self.filters_out 1]
temp_shape = values_out.get_shape().as_list()
values_out = tf.reshape(values_out,
[-1, temp_shape[1] * temp_shape[3]])
values_out = tf.reshape(
values_out, [-1, (self.seq - 1), temp_shape[1] * temp_shape[3]])
query_out = K.conv2d(query,
self.weight_query,
strides=(1, 1),
padding='valid',
data_format="channels_last"
) # [ batch , rest_window, 1, self.filters_out 1]
query_out = tf.reshape(query_out, [-1, temp_shape[1] * temp_shape[3]])
query_out = tf.expand_dims(query_out, 1)
score = self.V(tf.nn.tanh(values_out + query_out))
attention_weights = tf.nn.softmax(score, axis=1) #[batch , seq-1, 1]
values = tf.reshape(
values, [-1, (self.seq - 1), self.windows_size * self.filters_in])
context_vector = attention_weights * values
context_vector = tf.reduce_sum(context_vector, axis=1)
query = tf.reshape(query, [-1, self.windows_size * self.filters_in])
out = tf.concat([context_vector, query], axis=-1)
return out
def check_the_config_valid(para, window_size, feature):
initial_state = np.zeros((1, window_size, feature, 1))
initial_state = tf.cast(initial_state, 'float32')
initial_state = K.zeros_like(initial_state)
channel = 1
try:
for i in range(para["preprocessing_layers"]):
shape = (para["pre_kernel_width"], 1, channel,
para["pre_number_filters"])
channel = para["pre_number_filters"]
initial_state = K.conv2d(
initial_state, array_ops.zeros(tuple(shape)),
(para["pre_strides"],
1)) #,dilation_rate=(para["pre_dilation_rate"],1))
for i in range(1, 4):
assert len(para["eclstm_{}_recurrent_activation".format(i)]) == len(para["eclstm_{}_conv_activation".format(i)]) == \
len(para["eclstm_{}_number_filters".format(i)]) == len(para["eclstm_{}_kernel_width".format(i)])== \
len(para["eclstm_{}_fusion".format(i)]), "Archtecture Parameters of {} layer should be in same length".format(i)
for j in range(
len(para["eclstm_{}_recurrent_activation".format(i)])):
if para["eclstm_{}_recurrent_activation".format(i)][0] is None:
break
if para["eclstm_{}_fusion".format(i)][j] == "early":
shape = (para["eclstm_{}_kernel_width".format(i)][j],
feature, channel,
para["eclstm_{}_number_filters".format(i)][j])
feature = 1
channel = para["eclstm_{}_number_filters".format(i)][j]
else:
shape = (para["eclstm_{}_kernel_width".format(i)][j], 1,
channel,
para["eclstm_{}_number_filters".format(i)][j])
channel = para["eclstm_{}_number_filters".format(i)][j]
initial_state = K.conv2d(
initial_state, array_ops.zeros(tuple(shape)),
(para["eclstm_{}_strides".format(i)], 1))
print("valid Configuration!")
return True
except:
print(
"Invalid Configuration! Try smaller strides or kernel size or greater window size!"
)
return False
def call(self, inputs):
_, kernel_b = xnorize(self.kernel, self.H)
_, inputs_b = xnorize(inputs)
outputs = K.conv2d(inputs_b,
kernel_b,
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
# calculate Wa and xa
# kernel_a
mask = K.reshape(
self.kernel,
(-1,
self.filters)) # self.nb_row * self.nb_col * channels, filters
kernel_a = K.stop_gradient(K.mean(K.abs(mask), axis=0)) # filters
# inputs_a
if self.data_format == 'channels_first':
channel_axis = 1
else:
channel_axis = -1
mask = K.mean(K.abs(inputs), axis=channel_axis, keepdims=True)
ones = K.ones(self.kernel_size + (1, 1))
inputs_a = K.conv2d(mask,
ones,
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate
) # nb_sample, 1, new_nb_row, new_nb_col
if self.data_format == 'channels_first':
outputs = outputs * K.stop_gradient(inputs_a) * K.expand_dims(
K.expand_dims(K.expand_dims(kernel_a, 0), -1), -1)
else:
outputs = outputs * K.stop_gradient(inputs_a) * K.expand_dims(
K.expand_dims(K.expand_dims(kernel_a, 0), 0), 0)
if self.use_bias:
outputs = K.bias_add(outputs,
self.bias,
data_format=self.data_format)
if self.activation is not None:
return self.activation(outputs)
return outputs
def call(self, inputs, training=None):
def _l2normalize(v, eps=1e-12):
return v / (K.sum(v**2)**0.5 + eps)
def power_iteration(W, u):
_u = u
_v = _l2normalize(K.dot(_u, K.transpose(W)))
_u = _l2normalize(K.dot(_v, W))
return _u, _v
if self.spectral_normalization:
W_shape = self.kernel.shape.as_list()
# Flatten the Tensor
W_reshaped = K.reshape(self.kernel, [-1, W_shape[-1]])
_u, _v = power_iteration(W_reshaped, self.u)
# Calculate Sigma
sigma = K.dot(_v, W_reshaped)
sigma = K.dot(sigma, K.transpose(_u))
# normalize it
W_bar = W_reshaped / sigma
# reshape weight tensor
if training in {0, False}:
W_bar = K.reshape(W_bar, W_shape)
else:
with tf.control_dependencies([self.u.assign(_u)]):
W_bar = K.reshape(W_bar, W_shape)
# update weitht
self.kernel = W_bar
if self.rank == 1:
outputs = K.conv1d(inputs,
self.kernel,
strides=self.strides[0],
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate[0])
if self.rank == 2:
outputs = K.conv2d(inputs,
self.kernel,
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if self.rank == 3:
outputs = K.conv3d(inputs,
self.kernel,
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if self.use_bias:
outputs = K.bias_add(outputs,
self.bias,
data_format=self.data_format)
if self.activation is not None:
return self.activation(outputs)
return outputs
def recurrent_conv_u(self, x, w):
conv_out = K.conv2d(x,
w,
strides=(1, 1),
padding='same',
data_format='channels_last')
return conv_out
def recurrent_conv(self, x, w):
conv_out = K.conv2d(x,
w,
strides=(1, 1),
padding='same',
data_format=self.data_format)
return conv_out
def call(self, inputs, **kwargs):
if type(inputs) is list:
features = inputs[0]
else:
features = inputs
if self.weightnorm:
norm = tf.sqrt(
tf.reduce_sum(tf.square(self.kernel), (0, 1, 2)) + self.eps)
kernel = self.kernel / norm * self.wn_g
else:
kernel = self.kernel
features = K.conv2d(features,
kernel,
strides=self.strides,
padding=self.padding,
dilation_rate=self.dilation_rate)
if self.use_bias:
features = tf.add(features, self.bias)
if self.activation is not None:
features = self.activation(features)
return features
def soft_min_reg(cv, axis=None, min_disp=None, max_disp=None, labels=None):
if axis == 1:
cv = Lambda(lambda x: K.squeeze(x, axis=-1))(cv)
disp_map = K.reshape(
K.arange(min_disp,
max_disp - 0.000001, (max_disp - min_disp) / labels,
dtype="float32"), (1, 1, labels, 1))
if axis == 1:
output = K.conv2d(cv,
disp_map,
strides=(1, 1),
padding='valid',
data_format="channels_first")
x = K.expand_dims(K.squeeze(output, axis=1), axis=-1)
else:
x = K.conv2d(cv, disp_map, strides=(1, 1), padding='valid')
return x
def input_conv_u(self, x, w, b=None, padding='same'):
conv_out = K.conv2d(x, w, strides=self.strides,
padding=padding,
data_format='channels_last',
dilation_rate=self.dilation_rate)
if b is not None:
conv_out = K.bias_add(conv_out, b,
data_format='channels_last')
return conv_out
def _conv(self, x, w, b=None, padding='same'):
conv_out = K.conv2d(x,
w,
strides=(1, 1),
padding=padding,
data_format='channels_last')
if b is not None:
conv_out = K.bias_add(conv_out, b, data_format='channels_last')
return conv_out
def input_conv(self, x, w, b=None, padding='valid'):
conv_out = backend.conv2d(x, w, strides=self.strides,
padding=padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if b is not None:
conv_out = backend.bias_add(conv_out, b,
data_format=self.data_format)
return conv_out
def input_conv(self, x, w, b=None, padding='valid'):
conv_out = K.conv2d(x, w, strides=self.strides,
padding=padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if b is not None:
conv_out = K.bias_add(conv_out, b,
data_format=self.data_format)
return conv_out
def call(self, inputs): #?
scaled_kernel = self.kernel * self.runtime_coeff
if self.rank == 1:
kernel = Ke.pad(scaled_kernel
, [[1,1], [0,0], [0,0]])
fused_kernel = Ke.add_n([kernel[1:]
, kernel[:-1]]) / 2.0
outputs = K.conv1d(inputs
, fused_kernel
, strides=self.strides[0]
, padding=self.padding
, data_format=self.data_format
, dilation_rate=self.dilation_rate[0])
if self.rank == 2:
kernel = Ke.pad(scaled_kernel
, [[1,1], [1,1], [0,0], [0,0]])
fused_kernel = Ke.add_n([kernel[1:, 1:]
, kernel[:-1, 1:]
, kernel[1:, :-1]
, kernel[:-1, :-1]]) / 4.0
outputs = K.conv2d(inputs
, fused_kernel
, strides=self.strides
, padding=self.padding
, data_format=self.data_format
, dilation_rate=self.dilation_rate)
if self.rank == 3:
kernel = Ke.pad(scaled_kernel
, [[1,1], [1,1], [1,1], [0,0], [0,0]])
fused_kernel = Ke.add_n([kernel[1:, 1:, 1:]
, kernel[1:, 1:, :-1]
, kernel[1:, :-1, 1:]
, kernel[1:, :-1, :-1]
, kernel[:-1, 1:, 1:]
, kernel[:-1, 1:, :-1]
, kernel[:-1, :-1, 1:]
, kernel[:-1, :-1, :-1]]) / 8.0
outputs = K.conv3d(inputs
, fused_kernel
, strides=self.strides
, padding=self.padding
, data_format=self.data_format
, dilation_rate=self.dilation_rate)
if self.use_bias:
outputs = K.bias_add(outputs
, self.bias
, data_format=self.data_format)
if self.activation is not None:
return self.activation(outputs)
return outputs
def do_2d_convolution(feature_matrix,
kernel_matrix,
pad_edges=False,
stride_length_px=1):
"""Convolves 2-D feature maps with 2-D kernel.
m = number of rows in kernel
n = number of columns in kernel
c = number of output feature maps (channels)
:param feature_matrix: Input feature maps (numpy array). Dimensions must be
M x N x C or 1 x M x N x C.
:param kernel_matrix: Kernel as numpy array. Dimensions must be
m x n x C x c.
:param pad_edges: Boolean flag. If True, edges of input feature maps will
be zero-padded during convolution, so spatial dimensions of the output
feature maps will be the same (M x N). If False, dimensions
of the output maps will be (M - m + 1) x (N - n + 1).
:param stride_length_px: Stride length (pixels). The kernel will move by
this many rows or columns at a time as it slides over each input feature
map.
:return: feature_matrix: Output feature maps (numpy array). Dimensions will
be 1 x M x N x c or 1 x (M - m + 1) x (N - n + 1) x c, depending on
whether or not edges are padded.
"""
error_checking.assert_is_numpy_array_without_nan(feature_matrix)
error_checking.assert_is_numpy_array_without_nan(kernel_matrix)
error_checking.assert_is_numpy_array(kernel_matrix, num_dimensions=4)
error_checking.assert_is_boolean(pad_edges)
error_checking.assert_is_integer(stride_length_px)
error_checking.assert_is_geq(stride_length_px, 1)
if len(feature_matrix.shape) == 3:
feature_matrix = numpy.expand_dims(feature_matrix, axis=0)
error_checking.assert_is_numpy_array(feature_matrix, num_dimensions=4)
if pad_edges:
padding_string = 'same'
else:
padding_string = 'valid'
feature_tensor = K.conv2d(x=K.variable(feature_matrix),
kernel=K.variable(kernel_matrix),
strides=(stride_length_px, stride_length_px),
padding=padding_string,
data_format='channels_last')
return feature_tensor.numpy()
def apply_separate_filter_for_each_batch(inputs):
kernel = inputs[1]
x = K.expand_dims(inputs[0], axis=0)
outputs = K.conv2d(
x,
kernel,
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if self.bias is not None:
bias = inputs[2]
outputs = K.bias_add(outputs, bias, data_format=self.data_format)
return K.squeeze(outputs, axis=0)
def context_gating(self, x, w, rx, rw, b=None, padding='valid'):
input_shape = x.get_shape().as_list()
if self.data_format == 'channels_first':
x = K.pool2d(x, (input_shape[2], input_shape[3]), pool_mode='avg')
rx = K.pool2d(rx, (input_shape[2], input_shape[3]), pool_mode='avg')
elif self.data_format == 'channels_last':
x = K.pool2d(x, (input_shape[1], input_shape[2]), pool_mode='avg')
rx = K.pool2d(rx, (input_shape[1], input_shape[2]), pool_mode='avg')
conv_out1 = K.conv2d(
x,
w,
strides=self.strides,
padding=padding,
data_format=self.data_format)
conv_out2 = K.conv2d(
rx,
rw,
strides=self.strides,
padding=padding,
data_format=self.data_format)
conv_out = conv_out1 + conv_out2
if b is not None:
conv_out = K.bias_add(conv_out, b, data_format=self.data_format)
return conv_out
def call(self, inputs):
outputs = K.conv2d(inputs,
self.W_bar(),
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if self.use_bias:
outputs = K.bias_add(outputs,
self.bias,
data_format=self.data_format)
if self.activation is not None:
return self.activation(outputs)
return outputs
def correlation(self, displace, kernel):
""" Do the actual convolution==correlation.
"""
# Given an input tensor of shape [batch, in_height, in_width, in_channels]
displace = K.expand_dims(displace, 0) # 在开头增加一维
# a kernel tensor of shape [filter_height, filter_width, in_channels, out_channels]
kernel = K.expand_dims(kernel, 3) # 在末尾增加一维
# kernal去水平扫padding这一长条
out = K.conv2d(displace, kernel, padding='valid', data_format='channels_last')
out = K.squeeze(out, 0) # 扒掉开头的维度
# print(K.int_shape(out)) # （1,360,1）
return out
def call(self, inputs):
binary_kernel = binarize(self.kernel, H=self.H)
outputs = K.conv2d(inputs,
binary_kernel,
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if self.use_bias:
outputs = K.bias_add(outputs,
self.bias,
data_format=self.data_format)
if self.activation is not None:
return self.activation(outputs)
return outputs
def call(self, inputs, training=None):
input_transposed = tf.transpose(inputs, [3, 0, 1, 2, 4])
input_shape = tf.shape(input_transposed)
input_tensor_reshaped = tf.reshape(input_transposed, [
input_shape[0] * input_shape[1], self.input_height,
self.input_width, self.input_num_atoms
])
input_tensor_reshaped.set_shape(
(None, self.input_height, self.input_width, self.input_num_atoms))
conv = K.conv2d(input_tensor_reshaped,
self.W, (self.strides, self.strides),
padding=self.padding,
data_format='channels_last')
votes_shape = tf.shape(conv)
_, conv_height, conv_width, _ = conv.get_shape()
votes = tf.reshape(conv, [
input_shape[1], input_shape[0], votes_shape[1], votes_shape[2],
self.num_capsule, self.num_atoms
])
votes.set_shape((None, self.input_num_capsule, conv_height.value,
conv_width.value, self.num_capsule, self.num_atoms))
logit_shape = tf.stack([
input_shape[1], input_shape[0], votes_shape[1], votes_shape[2],
self.num_capsule
])
biases_replicated = tf.tile(
self.b, [conv_height.value, conv_width.value, 1, 1])
activations = update_routing(votes=votes,
biases=biases_replicated,
logit_shape=logit_shape,
num_dims=6,
input_dim=self.input_num_capsule,
output_dim=self.num_capsule,
num_routing=self.routings)
return activations
def call(self, inputs, training=None):
outputs = K.conv2d(
inputs,
self.compute_spectral_normal(training),
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if self.bias is not None:
outputs = K.bias_add(
outputs,
self.bias,
data_format=self.data_format)
if self.activation is not None:
return self.activation(outputs)
return outputs
def call(self, inputs):
# Mask kernel with connection matrix
masked_kernel = self.kernel * self.connections
# Apply convolution
if self.rank == 1:
outputs = K.conv1d(
inputs,
masked_kernel,
strides=self.strides[0],
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate[0])
if self.rank == 2:
outputs = K.conv2d(
inputs,
masked_kernel,
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if self.rank == 3:
outputs = K.conv3d(
inputs,
masked_kernel,
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if self.use_bias:
outputs = K.bias_add(
outputs,
self.bias,
data_format=self.data_format)
if self.activation is not None:
return self.activation(outputs)
return outputs
def max_singular_val_for_convolution(w,
u,
fully_differentiable=False,
ip=1,
padding='same',
strides=(1, 1),
data_format='channels_last'):
assert ip >= 1
if not fully_differentiable:
w_ = K.stop_gradient(w)
else:
w_ = w
u_bar = u
for _ in range(ip):
v_bar = K.conv2d(u_bar,
w_,
strides=strides,
data_format=data_format,
padding=padding)
v_bar = K.l2_normalize(v_bar)
u_bar_raw = K.conv2d_transpose(v_bar,
w_,
output_shape=K.int_shape(u),
strides=strides,
data_format=data_format,
padding=padding)
u_bar = K.l2_normalize(u_bar_raw)
u_bar_raw_diff = K.conv2d_transpose(v_bar,
w,
output_shape=K.int_shape(u),
strides=strides,
data_format=data_format,
padding=padding)
sigma = K.sum(u_bar * u_bar_raw_diff)
return sigma, u_bar
def call(self, inputs, training=None):
scaled_kernel = self.kernel * self.runtime_coeff
if self.rank == 1:
outputs = K.conv1d(
inputs,
scaled_kernel,
strides=self.strides[0],
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate[0])
if self.rank == 2:
outputs = K.conv2d(
inputs,
scaled_kernel,
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if self.rank == 3:
outputs = K.conv3d(
inputs,
scaled_kernel,
strides=self.strides,
padding=self.padding,
data_format=self.data_format,
dilation_rate=self.dilation_rate)
if self.use_bias:
outputs = K.bias_add(
outputs,
self.bias,
data_format=self.data_format)
if self.activation is not None:
outputs = self.activation(outputs)
return outputs
def offset_conv2d_eval(depth, padding, x):
"""Perform a conv2d on x with a given padding"""
kernel = K.variable(value=np.array([[[[1]] + [[0]] * (depth - 1)]]),
dtype='float32')
return K.conv2d(x, kernel, strides=(3, 3), padding=padding)
def call(self, features):
ni = features.shape[-1]
no = self.filters
if self.group == 'C4':
nt = 4
elif self.group == 'D4':
nt = 8
nti = 1 if self.first else nt
nto = nt
k = self.kernel_size[0]
t = np.reshape(np.arange(nti * k * k), (nti, k, k))
trafos = [np.rot90(t, k, axes=(1, 2)) for k in range(4)]
if nt == 8:
trafos = trafos + [np.flip(t, 1) for t in trafos]
self.trafos = trafos = np.array(trafos)
# index magic happens here
if nti == 1:
indices = trafos
elif nti == 4:
indices = [[trafos[l, (m - l) % 4, :, :] for m in range(4)]
for l in range(4)]
elif nti == 8:
indices = [[
trafos[l, (m - l) % 4 if ((m < 4) == (l < 4)) else
(m + l) % 4 + 4, :, :] for m in range(8)
] for l in range(8)]
self.indices = indices = np.reshape(indices, (nto, nti, k, k))
# transform the kernel
kernel = self.kernel
kernel = tf.reshape(kernel, (nti * k * k, ni, no))
kernel = tf.gather(kernel, indices, axis=0)
kernel = tf.reshape(kernel, (nto, nti, k, k, ni, no))
kernel = tf.transpose(kernel, (2, 3, 1, 4, 0, 5))
kernel = tf.reshape(kernel, (k, k, nti * ni, nto * no))
self.transformed_kernel = kernel
if self.first:
x = features
else:
s = features.shape
x = tf.reshape(features, (-1, s[1], s[2], s[3] * s[4]))
x = K.conv2d(x,
kernel,
strides=self.strides,
padding=self.padding,
dilation_rate=self.dilation_rate)
s = x.shape
x = tf.reshape(x, (-1, s[1], s[2], nto, no))
if self.use_bias:
features = tf.add(features, self.bias)
if self.activation is not None:
features = self.activation(features)
return x
def offset_conv2d_eval(depth, padding, x):
"""Perform a conv2d on x with a given padding"""
kernel = K.variable(value=np.array([[[[1]] + [[0]] * (depth - 1)]]),
dtype='float32')
return K.conv2d(x, kernel, strides=(3, 3), padding=padding)
def call(self, input_tensor, training=None):
input_transposed = tf.transpose(input_tensor, [3, 0, 1, 2, 4])
input_shape = K.shape(input_transposed)
input_tensor_reshaped = K.reshape(input_transposed, [
input_shape[1] * input_shape[0], self.input_height,
self.input_width, self.input_num_atoms
])
input_tensor_reshaped.set_shape(
(None, self.input_height, self.input_width, self.input_num_atoms))
if self.upsamp_type == 'resize':
upsamp = K.resize_images(input_tensor_reshaped, self.scaling,
self.scaling, 'channels_last')
outputs = K.conv2d(upsamp,
kernel=self.W,
strides=(1, 1),
padding=self.padding,
data_format='channels_last')
elif self.upsamp_type == 'subpix':
conv = K.conv2d(input_tensor_reshaped,
kernel=self.W,
strides=(1, 1),
padding='same',
data_format='channels_last')
outputs = tf.depth_to_space(conv, self.scaling)
else:
batch_size = input_shape[1] * input_shape[0]
# Infer the dynamic output shape:
out_height = deconv_output_length(input_length=self.input_height,
stride=self.scaling,
filter_size=self.kernel_size,
padding=self.padding)
out_width = deconv_output_length(input_length=self.input_width,
stride=self.scaling,
filter_size=self.kernel_size,
padding=self.padding)
output_shape = (batch_size, out_height, out_width,
self.num_capsule * self.num_atoms)
outputs = K.conv2d_transpose(input_tensor_reshaped,
self.W,
output_shape,
(self.scaling, self.scaling),
padding=self.padding,
data_format='channels_last')
votes_shape = K.shape(outputs)
_, conv_height, conv_width, _ = outputs.get_shape()
votes = K.reshape(outputs, [
input_shape[1], input_shape[0], votes_shape[1], votes_shape[2],
self.num_capsule, self.num_atoms
])
votes.set_shape((None, self.input_num_capsule, conv_height.value,
conv_width.value, self.num_capsule, self.num_atoms))
logit_shape = K.stack([
input_shape[1], input_shape[0], votes_shape[1], votes_shape[2],
self.num_capsule
])
biases_replicated = K.tile(self.b,
[votes_shape[1], votes_shape[2], 1, 1])
activations = update_routing(votes=votes,
biases=biases_replicated,
logit_shape=logit_shape,
num_dims=6,
input_dim=self.input_num_capsule,
output_dim=self.num_capsule,
num_routing=self.routings)
return activations
def recurrent_conv(self, x, w):
conv_out = K.conv2d(x, w, strides=(1, 1),
padding='same',
data_format=self.data_format)
return conv_out
def find_patch_matches(a, a_norm, b):
'''For each patch in A, find the best matching patch in B'''
# we want cross-correlation here so flip the kernels
convs = K.conv2d(a, b[:, :, ::-1, ::-1], border_mode='valid')
argmax = K.argmax(convs / a_norm, axis=1)
return argmax