def conv_layer(input, num_filters, filter_size, init, strides=(1,1), nonlinearity=relu):
if nonlinearity is None:
nonlinearity = lambda x: x
channel_count = input.shape[0]
b_param = parameter(shape=(num_filters, 1, 1))
w_param = parameter(shape=(num_filters, channel_count, filter_size[0], filter_size[1]), init=init)
r = convolution(w_param, input, (channel_count, strides[0], strides[1])) + b_param
r = nonlinearity(r)
return r
def Convolution(filter_shape, # e.g. (3,3)
num_filters=None, # e.g. 64 or None (which means 1 channel and don't add a dimension_
activation=activation_default_or_None,
init=init_default_or_glorot_uniform,
pad=pad_default_or_False,
strides=1,
sharing=True, # (must be True currently)
bias=bias_default_or_True,
init_bias=init_bias_default_or_0,
reduction_rank=1, # (must be 1 currently)
transpose=False, # (must be False currently)
max_temp_mem_size_in_samples=0):
#UntestedBranchError("Convolution")
activation = _resolve_activation(activation)
pad = pad if _is_given(pad ) else _current_default_options.pad
bias = bias if _is_given(bias) else _current_default_options.bias
# TODO: there must be a Python trick to do this as a function call on locals or so
if reduction_rank != 1:
NotImplementedError("Convolution: reduction_rank other than 1 currently not supported")
if transpose:
NotImplementedError("Convolution: transpose option currently not supported")
if not sharing:
NotImplementedError("Convolution: sharing option currently must be True")
output_channels_shape = _as_tuple(num_filters)
output_rank = len(output_channels_shape)
filter_rank = len(filter_shape)
kernel_shape = _INFERRED * reduction_rank + filter_shape # kernel := filter plus reductionDims
# parameters bound to this Function
#init_kernel = glorot_uniform(filter_rank=-filter_rank, output_rank=1)
init_kernel = _initializer_for(init, Record(filter_rank=filter_rank, output_rank=-1))
# BUGBUG: It is very confusing that output_rank is negative, esp. since that means count from the start. Solution: add a flag
W = Parameter(output_channels_shape + kernel_shape, init=init_kernel, name='W') # (K, C, H, W) aka [ W x H x C x K ]
b = Parameter(output_channels_shape + (1,) * len(filter_shape), init=init_bias, name='b') if bias else None # (K, 1, 1) aka [ 1 x 1 x K ]
# expression
x = Placeholder(name='convolution_arg')
# TODO: update the parameter order of convolution() to match the optional ones as in here? (options order matches Keras)
apply_x = convolution (W, x,
strides=_as_tuple(strides),
sharing=_as_tuple(sharing),
auto_padding=_as_tuple(pad),
# TODO: can we rename auto_padding to pad?
transpose=transpose,
max_temp_mem_size_in_samples=max_temp_mem_size_in_samples)
if bias:
apply_x = apply_x + b
apply_x = apply_x >> activation
return Block(apply_x, 'Convolution', Record(W=W, b=b))
def Convolution(filter_shape, # e.g. (3,3)
num_filters=None, # e.g. 64 or None (which means 1 channel and don't add a dimension_
activation=activation_default_or_None,
init=init_default_or_glorot_uniform,
pad=pad_default_or_False,
strides=1,
sharing=True, # (must be True currently)
bias=bias_default_or_True,
init_bias=init_bias_default_or_0,
reduction_rank=1, # (must be 1 currently)
transpose=False, # (must be False currently)
max_temp_mem_size_in_samples=0):
#UntestedBranchError("Convolution")
activation = _resolve_activation(activation)
pad = pad if _is_given(pad ) else _current_default_options.pad
bias = bias if _is_given(bias) else _current_default_options.bias
# TODO: there must be a Python trick to do this as a function call on locals or so
if reduction_rank != 1:
NotImplementedError("Convolution: reduction_rank other than 1 currently not supported")
if transpose:
NotImplementedError("Convolution: transpose option currently not supported")
if not sharing:
NotImplementedError("Convolution: sharing option currently must be True")
output_channels_shape = _as_tuple(num_filters)
output_rank = len(output_channels_shape)
filter_rank = len(filter_shape)
kernel_shape = _INFERRED * reduction_rank + filter_shape # kernel := filter plus reductionDims
# parameters bound to this Function
#init_kernel = glorot_uniform(filter_rank=-filter_rank, output_rank=1)
init_kernel = _initializer_for(init, Record(filter_rank=filter_rank, output_rank=-1))
# BUGBUG: It is very confusing that output_rank is negative, esp. since that means count from the start. Solution: add a flag
W = Parameter(output_channels_shape + kernel_shape, init=init_kernel, name='W') # (K, C, H, W) aka [ W x H x C x K ]
b = Parameter(output_channels_shape + (1,) * len(filter_shape), init=init_bias, name='b') if bias else None # (K, 1, 1) aka [ 1 x 1 x K ]
# expression
x = Placeholder(name='convolution_arg')
# TODO: update the parameter order of convolution() to match the optional ones as in here? (options order matches Keras)
apply_x = convolution (W, x,
strides=_as_tuple(strides),
sharing=_as_tuple(sharing),
auto_padding=_as_tuple(pad),
# TODO: can we rename auto_padding to pad?
transpose=transpose,
max_temp_mem_size_in_samples=max_temp_mem_size_in_samples)
if bias:
apply_x = apply_x + b
apply_x = apply_x >> activation
return Block(apply_x, 'Convolution', Record(W=W, b=b))
def convolution(input, name, **kwargs):
dim = __weights_dict[name]['weights'].ndim
weight = np.transpose(__weights_dict[name]['weights'],
[dim - 1, dim - 2] + list(range(0, dim - 2)))
w = cntk.Parameter(init=weight, name=name + '_weight')
input = cntk.transpose(input, [dim - 2] + list(range(0, dim - 2)))
layer = ops.convolution(w, input, **kwargs)
if 'bias' in __weights_dict[name]:
bias = np.reshape(__weights_dict[name]['bias'], [-1] + [1] * (dim - 2))
b = cntk.Parameter(init=bias, name=name + '_bias')
layer = layer + b
layer = cntk.transpose(layer, list(range(1, dim - 1)) + [0])
return layer
def _conv_ops(weights, data):
return ops.convolution(weights, data, strides=(cntk.InferredDimension, ) + \
ops.sanitize_shape(stride), auto_padding=[False, pad, pad])
def _conv_ops(weights, data):
return ops.convolution(weights, data, strides=(cntk.InferredDimension, ) + \
ops.sanitize_shape(stride), auto_padding=[False, pad, pad])