def call(self, inputs):
inputs, activation = inputs
# 1. space to batch
batched = cl.space_to_batch_nd(inputs, self.kernel_size, self.strides)
activation = cl.space_to_batch_nd(activation, self.kernel_size,
self.strides)
# 2. transforming
vote = self.transforming(batched)
# 3. routing
pose, activation = self.routing(vote, activation)
return pose, activation
def call(self, inputs):
inputs, activation = inputs
# 1. space to batch
# patching everything into [batch_size, out_height, out_width, in_channels] + in_caps_dims (batched)
# and [batch_size, out_height, out_width, in_channels] (activation).
batched = cl.space_to_batch_nd(inputs, self.kernel_size, self.strides)
activation = cl.space_to_batch_nd(activation, self.kernel_size,
self.strides)
# 2. transforming
# transforming to [batch_size, out_height, out_width, in_channels, out_channels/filters] + out_caps_dims
vote = self.transforming(batched)
# 3. routing
pose, activation = self.routing(vote, activation)
return pose, activation
def conv2d(inputs,
activation,
filters,
out_caps_dims,
kernel_size,
strides,
padding="valid",
routing_method="EMRouting",
name=None,
reuse=None):
"""A 2D convolutional capsule layer.
Args:
inputs: A 6-D tensor with shape [batch_size, in_height, in_width, in_channels] + in_caps_dims.
activation: A 4-D tensor with shape [batch_size, in_height, in_width, in_channels].
filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution).
out_caps_dims: A tuple/list of 2 integers, specifying the dimensions of output capsule, e.g. out_caps_dims=[4, 4] representing that each output capsule has shape [4, 4].
kernel_size: An integer or tuple/list of 2 integers, specifying the height and width of the 2D convolution window. Can be a single integer to specify the same value for all spatial dimensions.
strides: An integer or tuple/list of 2 integers, specifying the strides of the convolution along the height and width. Can be a single integer to specify the same value for all spatial dimensions.
padding: One of "valid" or "same" (case-insensitive), now only support "valid".
routing_method: One of "EMRouting" or "DynamicRouting", the method of routing-by-agreement algorithm.
name: A string, the name of the layer.
reuse: Boolean, whether to reuse the weights of a previous layer by the same name.
Returns:
pose: A 6-D tensor with shape [batch_size, out_height, out_width, out_channels] + out_caps_dims.
activation: A 4-D tensor with shape [batch_size, out_height, out_width, out_channels].
"""
name = "conv2d" if name is None else name
with tf.variable_scope(name) as scope:
if reuse:
scope.reuse_variables()
input_shape = cl.shape(inputs)
input_rank = len(input_shape)
activation_rank = len(activation.shape)
if not input_rank == 6:
raise ValueError('Inputs to `conv2d` should have rank 6. Received inputs rank:', str(input_rank))
if not activation_rank == 4:
raise ValueError('Activation to `conv2d` should have rank 4. Received activation rank:', str(activation_rank))
if isinstance(kernel_size, int):
kernel_size = [kernel_size, kernel_size, input_shape[3]]
elif isinstance(kernel_size, (list, tuple)) and len(kernel_size) == 2:
kernel_size = [kernel_size[0], kernel_size[1], input_shape[3]]
else:
raise ValueError('"kernel_size" should be an integer or tuple/list of 2 integers. Received:', str(kernel_size))
if isinstance(strides, int):
strides = [strides, strides, 1]
elif isinstance(strides, (list, tuple)) and len(strides) == 2:
strides = [strides[0], strides[1], 1]
else:
raise ValueError('"strides" should be an integer or tuple/list of 2 integers. Received:', str(kernel_size))
if not isinstance(out_caps_dims, (list, tuple)) or len(out_caps_dims) != 2:
raise ValueError('"out_caps_dims" should be a tuple/list of 2 integers. Received:', str(out_caps_dims))
elif isinstance(out_caps_dims, tuple):
out_caps_dims = list(out_caps_dims)
# 1. space to batch
# patching everything into [batch_size, out_height, out_width, in_channels] + in_caps_dims (batched)
# and [batch_size, out_height, out_width, in_channels] (activation).
batched = cl.space_to_batch_nd(inputs, kernel_size, strides)
activation = cl.space_to_batch_nd(activation, kernel_size, strides)
# 2. transforming
# transforming to [batch_size, out_height, out_width, in_channels, out_channels/filters] + out_caps_dims
vote = transforming(batched,
num_outputs=filters,
out_caps_dims=out_caps_dims)
# 3. routing
pose, activation = routing(vote, activation, method=routing_method)
return pose, activation
def conv3d(inputs,
activation,
filters,
out_caps_dims,
kernel_size,
strides,
padding="valid",
routing_method="EMRouting",
name=None,
reuse=None):
"""A 3D convolutional capsule layer.
Args:
inputs: A 7-D tensor with shape [batch_size, in_depth, in_height, in_width, in_channels] + in_caps_dims.
activation: A 5-D tensor with shape [batch_size, in_depth, in_height, in_width, in_channels].
filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution).
out_caps_dims: A tuple/list of 2 integers, specifying the dimensions of output capsule, e.g. out_caps_dims=[4, 4] representing that each output capsule has shape [4, 4].
kernel_size: An integer or tuple/list of 3 integers, specifying the height and width of the 3D convolution window. Can be a single integer to specify the same value for all spatial dimensions.
strides: An integer or tuple/list of 3 integers, specifying the strides of the convolution along the height and width. Can be a single integer to specify the same value for all spatial dimensions.
padding: One of "valid" or "same" (case-insensitive), now only support "valid".
routing_method: One of "EMRouting" or "DynamicRouting", the method of routing-by-agreement algorithm.
name: String, a name for the operation (optional).
reuse: Boolean, whether to reuse the weights of a previous layer by the same name.
Returns:
pose: A 7-D tensor with shape [batch_size, out_depth, out_height, out_width, out_channels] + out_caps_dims.
activation: A 5-D tensor with shape [batch_size, out_depth, out_height, out_width, out_channels].
"""
name = "conv1d" if name is None else name
with tf.name_scope(name):
input_shape = cl.shape(inputs)
input_rank = len(input_shape)
activation_rank = len(activation.shape)
if input_rank != 7:
raise ValueError('Inputs to `conv3d` should have rank 7. Received input rank:', str(input_rank))
if activation_rank != 5:
raise ValueError('Activation to `conv3d` should have rank 5. Received input shape:', str(activation_rank))
if isinstance(kernel_size, int):
kernel_size = [kernel_size, kernel_size, kernel_size]
elif isinstance(kernel_size, (list, tuple)) and len(kernel_size) == 3:
kernel_size = kernel_size
else:
raise ValueError('"kernel_size" should be an integer or tuple/list of 3 integers. Received:', str(kernel_size))
if isinstance(strides, int):
strides = [strides, strides, strides]
elif isinstance(strides, (list, tuple)) and len(strides) == 3:
strides = strides
else:
raise ValueError('"strides" should be an integer or tuple/list of 3 integers. Received:', str(strides))
if not isinstance(out_caps_dims, (list, tuple)) or len(out_caps_dims) != 2:
raise ValueError('"out_caps_dims" should be a tuple/list of 2 integers. Received:', str(out_caps_dims))
elif isinstance(out_caps_dims, tuple):
out_caps_dims = list(out_caps_dims)
# 1. space to batch
batched = cl.space_to_batch_nd(inputs, kernel_size, strides)
activation = cl.space_to_batch_nd(activation, kernel_size, strides)
# 2. transforming
vote = transforming(batched,
num_outputs=filters,
out_caps_dims=out_caps_dims)
# 3. routing
pose, activation = routing(vote, activation, method=routing_method)
return pose, activation