def N_conv(x,
kernel,
strides=(1, 1),
padding='valid',
data_format=None,
dilation_rate=(1, 1)):
data_format = normalize_data_format(data_format)
x, tf_data_format = _preprocess_conv2d_input(x, data_format)
padding = _preprocess_padding(padding)
# TF 2 arg conversion
kwargs = {}
if _is_tf_1():
kwargs['dilation_rate'] = dilation_rate
else:
kwargs['dilations'] = dilation_rate
x = conv2d_cosnorm(x, kernel, strides=strides, padding=padding)
if data_format == 'channels_first' and tf_data_format == 'NHWC':
x = tf.transpose(x, (0, 3, 1, 2)) # NHWC -> NCHW
return x
def call(self, inputs):
if self.data_format is None:
data_format = image_data_format()
if self.data_format not in {'channels_first', 'channels_last'}:
raise ValueError('Unknown data_format ' + str(data_format))
x = _preprocess_conv2d_input(inputs, self.data_format)
padding = _preprocess_padding(self.padding)
strides = (1,) + self.strides + (1,)
outputs = tf.nn.depthwise_conv2d(inputs, self.depthwise_kernel,
strides=strides,
padding=padding,
rate=self.dilation_rate)
if self.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 depth_to_space(input, scale, data_format=None):
''' Uses phase shift algorithm to convert channels/depth for spatial resolution '''
if data_format is None:
data_format = image_data_format()
data_format = data_format.lower()
input = _preprocess_conv2d_input(input, data_format)
out = tf.depth_to_space(input, scale)
out = _postprocess_conv2d_output(out, data_format)
return out
def conv2d(x,
kernel,
strides=(1, 1),
padding='valid',
data_format=None,
dilation_rate=(1, 1)):
"""2D convolution.
# Arguments
x: Tensor or variable.
kernel: kernel tensor.
strides: strides tuple.
padding: string, `"same"`, `"causal"` or `"valid"`.
data_format: string, `"channels_last"` or `"channels_first"`.
Whether to use Theano or TensorFlow/CNTK data format
for inputs/kernels/outputs.
dilation_rate: tuple of 2 integers.
# Returns
A tensor, result of 2D convolution.
# Raises
ValueError: If `data_format` is neither
`"channels_last"` nor `"channels_first"`.
"""
data_format = K.normalize_data_format(data_format)
# ADDED
kernel_shape = kernel.get_shape().as_list()
if padding == 'causal':
if data_format != 'channels_last':
raise ValueError('When using causal padding in `conv2d`, '
'`data_format` must be "channels_last" '
'(temporal data).')
# causal (dilated) convolution:
left_pad = dilation_rate[0] * (kernel_shape[0] - 1)
x = temporal_2d_padding(x, (left_pad, 0), data_format=data_format)
padding = 'valid'
# ADDED till here
x, tf_data_format = _preprocess_conv2d_input(x, data_format)
padding = _preprocess_padding(padding)
x = tf.nn.convolution(input=x,
filter=kernel,
dilation_rate=dilation_rate,
strides=strides,
padding=padding,
data_format=tf_data_format)
if data_format == 'channels_first' and tf_data_format == 'NHWC':
x = tf.transpose(x, (0, 3, 1, 2)) # NHWC -> NCHW
return x
def separable_conv2d(x, depthwise_kernel, pointwise_kernel, strides=(1, 1),
padding='valid', data_format=None, dilation_rate=(1, 1)):
"""2D convolution with separable filters.
# Arguments
x: input tensor
depthwise_kernel: convolution kernel for the depthwise convolution.
pointwise_kernel: kernel for the 1x1 convolution.
strides: strides tuple (length 2).
padding: string, `"same"` or `"valid"`.
data_format: string, `"channels_last"` or `"channels_first"`.
dilation_rate: tuple of integers,
dilation rates for the separable convolution.
# Returns
Output tensor.
# Raises
ValueError: If `data_format` is neither
`"channels_last"` nor `"channels_first"`.
"""
data_format = normalize_data_format(data_format)
# ADDED
kernel_shape = depthwise_kernel.get_shape().as_list()
if padding == 'causal':
if data_format != 'channels_last':
raise ValueError('When using causal padding in `conv1d`, '
'`data_format` must be "channels_last" '
'(temporal data).')
left_pad = dilation_rate * (kernel_shape[0] - 1)
x = temporal_padding(x, (left_pad, 0))
padding = 'valid'
# ADDED till here
x, tf_data_format = _preprocess_conv2d_input(x, data_format)
padding = _preprocess_padding(padding)
if tf_data_format == 'NHWC':
strides = (1,) + strides + (1,)
else:
strides = (1, 1) + strides
x = tf.nn.separable_conv2d(x, depthwise_kernel, pointwise_kernel,
strides=strides,
padding=padding,
rate=dilation_rate,
data_format=tf_data_format)
if data_format == 'channels_first' and tf_data_format == 'NHWC':
x = tf.transpose(x, (0, 3, 1, 2)) # NHWC -> NCHW
return x
def pool2d_argmax(x: 'Tensor',
pool_size: tuple,
strides: tuple = (1, 1),
padding: str = 'valid',
data_format: str = None) -> tuple:
"""
2D Pooling that returns indexes too.
Args:
x: Tensor or variable.
pool_size: tuple of 2 integers.
strides: tuple of 2 integers.
padding: string, `"same"` or `"valid"`.
data_format: string, `"channels_last"` or `"channels_first"`.
Returns:
A tensor, result of 2D pooling.
Raises:
ValueError: if `data_format` is neither `"channels_last"` or `"channels_first"`.
"""
# get the normalized data format
data_format = K.common.normalize_data_format(data_format)
# pre-process the input tensor
x, tf_data_format = _preprocess_conv2d_input(x, data_format)
padding = _preprocess_padding(padding)
# update strides and pool size based on data format
if tf_data_format == 'NHWC':
strides = (1, ) + strides + (1, )
pool_size = (1, ) + pool_size + (1, )
else:
strides = (1, 1) + strides
pool_size = (1, 1) + pool_size
# get the values and the indexes from the max pool operation
x, idx = tf.nn.max_pool_with_argmax(x, pool_size, strides, padding)
# update shapes if necessary
if data_format == 'channels_first' and tf_data_format == 'NHWC':
# NHWC -> NCHW
x = tf.transpose(x, (0, 3, 1, 2))
# NHWC -> NCHW
idx = tf.transpose(idx, (0, 3, 1, 2))
return x, idx
def call(self, inputs, training=None):
inputs = _preprocess_conv2d_input(inputs, self.data_format)
outputs = tf.nn.depthwise_conv2d(inputs,
self.depthwise_kernel,
strides=self._strides,
padding=self._padding,
rate=self.dilation_rate,
data_format=self._data_format)
outputs = _postprocess_conv2d_output(outputs, self.data_format)
if self.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
