def conv2d_fixed_padding(inputs,
filters,
kernel_size,
strides,
data_format="channels_first",
use_td=False,
targeting_rate=None,
keep_prob=None,
is_training=None):
"""Strided 2-D convolution with explicit padding.
The padding is consistent and is based only on `kernel_size`, not on the
dimensions of `inputs` (as opposed to using `tf.layers.conv2d` alone).
Args:
inputs: `Tensor` of size `[batch, channels, height_in, width_in]`.
filters: `int` number of filters in the convolution.
kernel_size: `int` size of the kernel to be used in the convolution.
strides: `int` strides of the convolution.
data_format: `str` either "channels_first" for `[batch, channels, height,
width]` or "channels_last for `[batch, height, width, channels]`.
use_td: `str` one of "weight" or "unit". Set to False or "" to disable
targeted dropout.
targeting_rate: `float` proportion of weights to target with targeted
dropout.
keep_prob: `float` keep probability for targeted dropout.
is_training: `bool` for whether the model is in training.
Returns:
A `Tensor` of shape `[batch, filters, height_out, width_out]`.
Raises:
Exception: if use_td is not valid.
"""
if strides > 1:
inputs = fixed_padding(inputs, kernel_size, data_format=data_format)
if use_td:
inputs_shape = common_layers.shape_list(inputs)
if use_td == "weight":
if data_format == "channels_last":
size = kernel_size * kernel_size * inputs_shape[-1]
else:
size = kernel_size * kernel_size * inputs_shape[1]
targeting_count = targeting_rate * tf.to_float(size)
targeting_fn = common_layers.weight_targeting
elif use_td == "unit":
targeting_count = targeting_rate * filters
targeting_fn = common_layers.unit_targeting
else:
raise Exception("Unrecognized targeted dropout type: %s" % use_td)
y = common_layers.td_conv(
inputs,
filters,
kernel_size,
targeting_count,
targeting_fn,
keep_prob,
is_training,
do_prune=True,
strides=strides,
padding=("SAME" if strides == 1 else "VALID"),
data_format=data_format,
use_bias=False,
kernel_initializer=tf.variance_scaling_initializer())
else:
y = layers().Conv2D(
filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=("SAME" if strides == 1 else "VALID"),
use_bias=False,
kernel_initializer=tf.variance_scaling_initializer(),
data_format=data_format)(inputs)
# added by mjc: to see the activation distribution
tf.summary.histogram('activations', y)
return y
def conv2d_fixed_padding(inputs,
filters,
kernel_size,
strides,
data_format="channels_first",
use_td=False,
targeting_rate=None,
keep_prob=None,
is_training=None):
"""Strided 2-D convolution with explicit padding.
The padding is consistent and is based only on `kernel_size`, not on the
dimensions of `inputs` (as opposed to using `tf.layers.conv2d` alone).
Args:
inputs: `Tensor` of size `[batch, channels, height_in, width_in]`.
filters: `int` number of filters in the convolution.
kernel_size: `int` size of the kernel to be used in the convolution.
strides: `int` strides of the convolution.
data_format: `str` either "channels_first" for `[batch, channels, height,
width]` or "channels_last for `[batch, height, width, channels]`.
use_td: `str` one of "weight" or "unit". Set to False or "" to disable
targeted dropout.
targeting_rate: `float` proportion of weights to target with targeted
dropout.
keep_prob: `float` keep probability for targeted dropout.
is_training: `bool` for whether the model is in training.
Returns:
A `Tensor` of shape `[batch, filters, height_out, width_out]`.
Raises:
Exception: if use_td is not valid.
"""
if strides > 1:
inputs = fixed_padding(inputs, kernel_size, data_format=data_format)
if use_td:
inputs_shape = common_layers.shape_list(inputs)
if use_td == "weight":
if data_format == "channels_last":
size = kernel_size * kernel_size * inputs_shape[-1]
else:
size = kernel_size * kernel_size * inputs_shape[1]
targeting_count = targeting_rate * tf.to_float(size)
targeting_fn = common_layers.weight_targeting
elif use_td == "unit":
targeting_count = targeting_rate * filters
targeting_fn = common_layers.unit_targeting
else:
raise Exception("Unrecognized targeted dropout type: %s" % use_td)
y = common_layers.td_conv(
inputs,
filters,
kernel_size,
targeting_count,
targeting_fn,
keep_prob,
is_training,
do_prune=True,
strides=strides,
padding=("SAME" if strides == 1 else "VALID"),
data_format=data_format,
use_bias=False,
kernel_initializer=tf.variance_scaling_initializer())
else:
y = tf.layers.conv2d(
inputs=inputs,
filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=("SAME" if strides == 1 else "VALID"),
use_bias=False,
kernel_initializer=tf.variance_scaling_initializer(),
data_format=data_format)
return y
