def build(self, input_shape):
height = input_shape[1]
width = input_shape[2]
channels = input_shape[3]
norm_layer = (tf.keras.layers.experimental.SyncBatchNormalization
if self._use_sync_bn else
tf.keras.layers.BatchNormalization)
norm_with_quantize = helper.BatchNormalizationQuantized(norm_layer)
norm_no_quantize = helper.BatchNormalizationNoQuantized(norm_layer)
norm = helper.norm_by_activation(self._activation, norm_with_quantize,
norm_no_quantize)
self.aspp_layers = []
conv1 = helper.Conv2DQuantized(
filters=self._output_channels,
kernel_size=(1, 1),
kernel_initializer=self._kernel_initializer,
kernel_regularizer=self._kernel_regularizer,
use_bias=False,
activation=helper.NoOpActivation())
norm1 = norm(axis=self._bn_axis,
momentum=self._batchnorm_momentum,
epsilon=self._batchnorm_epsilon)
self.aspp_layers.append([conv1, norm1])
for dilation_rate in self._dilation_rates:
leading_layers = []
kernel_size = (3, 3)
if self._use_depthwise_convolution:
leading_layers += [
helper.DepthwiseConv2DOutputQuantized(
depth_multiplier=1,
kernel_size=kernel_size,
padding='same',
depthwise_regularizer=self._kernel_regularizer,
depthwise_initializer=self._kernel_initializer,
dilation_rate=dilation_rate,
use_bias=False,
activation=helper.NoOpActivation())
]
kernel_size = (1, 1)
conv_dilation = leading_layers + [
helper.Conv2DQuantized(
filters=self._output_channels,
kernel_size=kernel_size,
padding='same',
kernel_regularizer=self._kernel_regularizer,
kernel_initializer=self._kernel_initializer,
dilation_rate=dilation_rate,
use_bias=False,
activation=helper.NoOpActivation())
]
norm_dilation = norm(axis=self._bn_axis,
momentum=self._batchnorm_momentum,
epsilon=self._batchnorm_epsilon)
self.aspp_layers.append(conv_dilation + [norm_dilation])
if self._pool_kernel_size is None:
pooling = [
helper.GlobalAveragePooling2DQuantized(),
helper.ReshapeQuantized((1, 1, channels))
]
else:
pooling = [
helper.AveragePooling2DQuantized(self._pool_kernel_size)
]
conv2 = helper.Conv2DQuantized(
filters=self._output_channels,
kernel_size=(1, 1),
kernel_initializer=self._kernel_initializer,
kernel_regularizer=self._kernel_regularizer,
use_bias=False,
activation=helper.NoOpActivation())
norm2 = norm(axis=self._bn_axis,
momentum=self._batchnorm_momentum,
epsilon=self._batchnorm_epsilon)
self.aspp_layers.append(pooling + [conv2, norm2])
self._resizing_layer = helper.ResizingQuantized(
height, width, interpolation=self._interpolation)
self._projection = [
helper.Conv2DQuantized(filters=self._output_channels,
kernel_size=(1, 1),
kernel_initializer=self._kernel_initializer,
kernel_regularizer=self._kernel_regularizer,
use_bias=False,
activation=helper.NoOpActivation()),
norm_with_quantize(axis=self._bn_axis,
momentum=self._batchnorm_momentum,
epsilon=self._batchnorm_epsilon)
]
self._dropout_layer = tf.keras.layers.Dropout(rate=self._dropout)
self._concat_layer = helper.ConcatenateQuantized(axis=-1)
def build(self, input_shape: Sequence[tf.TensorShape]):
"""Creates the variables of the segmentation head."""
# When input_shape is a list/tuple, the first corresponds to backbone
# features used for resizing the decoder features (the second) if feature
# fusion type is `deeplabv3plus`.
backbone_shape = input_shape[0]
use_depthwise_convolution = self._config_dict[
'use_depthwise_convolution']
random_initializer = tf.keras.initializers.RandomNormal(stddev=0.01)
conv_kwargs = {
'kernel_size': 3 if not use_depthwise_convolution else 1,
'padding': 'same',
'use_bias': False,
'kernel_initializer': random_initializer,
'kernel_regularizer': self._config_dict['kernel_regularizer'],
}
norm_layer = (tf.keras.layers.experimental.SyncBatchNormalization
if self._config_dict['use_sync_bn'] else
tf.keras.layers.BatchNormalization)
norm_with_quantize = helper.BatchNormalizationQuantized(norm_layer)
norm_no_quantize = helper.BatchNormalizationNoQuantized(norm_layer)
norm = helper.norm_by_activation(self._config_dict['activation'],
norm_with_quantize, norm_no_quantize)
bn_kwargs = {
'axis': self._bn_axis,
'momentum': self._config_dict['norm_momentum'],
'epsilon': self._config_dict['norm_epsilon'],
}
if self._config_dict['feature_fusion'] == 'deeplabv3plus':
# Deeplabv3+ feature fusion layers.
self._dlv3p_conv = helper.Conv2DQuantized(
kernel_size=1,
padding='same',
use_bias=False,
kernel_initializer=tf.keras.initializers.RandomNormal(
stddev=0.01),
kernel_regularizer=self._config_dict['kernel_regularizer'],
name='segmentation_head_deeplabv3p_fusion_conv',
filters=self._config_dict['low_level_num_filters'],
activation=helper.NoOpActivation())
self._dlv3p_norm = norm(
name='segmentation_head_deeplabv3p_fusion_norm', **bn_kwargs)
# Segmentation head layers.
self._convs = []
self._norms = []
for i in range(self._config_dict['num_convs']):
if use_depthwise_convolution:
self._convs.append(
helper.DepthwiseConv2DQuantized(
name='segmentation_head_depthwise_conv_{}'.format(i),
kernel_size=3,
padding='same',
use_bias=False,
depthwise_initializer=random_initializer,
depthwise_regularizer=self.
_config_dict['kernel_regularizer'],
depth_multiplier=1,
activation=helper.NoOpActivation()))
norm_name = 'segmentation_head_depthwise_norm_{}'.format(i)
self._norms.append(norm(name=norm_name, **bn_kwargs))
conv_name = 'segmentation_head_conv_{}'.format(i)
self._convs.append(
helper.Conv2DQuantized(
name=conv_name,
filters=self._config_dict['num_filters'],
activation=helper.NoOpActivation(),
**conv_kwargs))
norm_name = 'segmentation_head_norm_{}'.format(i)
self._norms.append(norm(name=norm_name, **bn_kwargs))
self._classifier = helper.Conv2DOutputQuantized(
name='segmentation_output',
filters=self._config_dict['num_classes'],
kernel_size=self._config_dict['prediction_kernel_size'],
padding='same',
bias_initializer=tf.zeros_initializer(),
kernel_initializer=tf.keras.initializers.RandomNormal(stddev=0.01),
kernel_regularizer=self._config_dict['kernel_regularizer'],
bias_regularizer=self._config_dict['bias_regularizer'],
activation=helper.NoOpActivation())
self._upsampling_layer = helper.UpSampling2DQuantized(
size=(self._config_dict['upsample_factor'],
self._config_dict['upsample_factor']),
interpolation='nearest')
self._resizing_layer = tf.keras.layers.Resizing(
backbone_shape[1], backbone_shape[2], interpolation='bilinear')
self._concat_layer = helper.ConcatenateQuantized(axis=self._bn_axis)
super().build(input_shape)
def __init__(
self,
filters: int,
strides: int,
dilation_rate: int = 1,
use_projection: bool = False,
se_ratio: Optional[float] = None,
resnetd_shortcut: bool = False,
stochastic_depth_drop_rate: Optional[float] = None,
kernel_initializer: str = 'VarianceScaling',
kernel_regularizer: tf.keras.regularizers.Regularizer = None,
bias_regularizer: tf.keras.regularizers.Regularizer = None,
activation: str = 'relu',
use_sync_bn: bool = False,
norm_momentum: float = 0.99,
norm_epsilon: float = 0.001,
bn_trainable: bool = True, # pytype: disable=annotation-type-mismatch # typed-keras
**kwargs):
"""Initializes a standard bottleneck block with BN after convolutions.
Args:
filters: An `int` number of filters for the first two convolutions. Note
that the third and final convolution will use 4 times as many filters.
strides: An `int` block stride. If greater than 1, this block will
ultimately downsample the input.
dilation_rate: An `int` dilation_rate of convolutions. Default to 1.
use_projection: A `bool` for whether this block should use a projection
shortcut (versus the default identity shortcut). This is usually `True`
for the first block of a block group, which may change the number of
filters and the resolution.
se_ratio: A `float` or None. Ratio of the Squeeze-and-Excitation layer.
resnetd_shortcut: A `bool`. If True, apply the resnetd style modification
to the shortcut connection.
stochastic_depth_drop_rate: A `float` or None. If not None, drop rate for
the stochastic depth layer.
kernel_initializer: A `str` of kernel_initializer for convolutional
layers.
kernel_regularizer: A `tf.keras.regularizers.Regularizer` object for
Conv2D. Default to None.
bias_regularizer: A `tf.keras.regularizers.Regularizer` object for Conv2d.
Default to None.
activation: A `str` name of the activation function.
use_sync_bn: A `bool`. If True, use synchronized batch normalization.
norm_momentum: A `float` of normalization momentum for the moving average.
norm_epsilon: A `float` added to variance to avoid dividing by zero.
bn_trainable: A `bool` that indicates whether batch norm layers should be
trainable. Default to True.
**kwargs: Additional keyword arguments to be passed.
"""
super(BottleneckBlockQuantized, self).__init__(**kwargs)
self._filters = filters
self._strides = strides
self._dilation_rate = dilation_rate
self._use_projection = use_projection
self._se_ratio = se_ratio
self._resnetd_shortcut = resnetd_shortcut
self._use_sync_bn = use_sync_bn
self._activation = activation
self._stochastic_depth_drop_rate = stochastic_depth_drop_rate
self._kernel_initializer = kernel_initializer
self._norm_momentum = norm_momentum
self._norm_epsilon = norm_epsilon
self._kernel_regularizer = kernel_regularizer
self._bias_regularizer = bias_regularizer
norm_layer = (tf.keras.layers.experimental.SyncBatchNormalization
if use_sync_bn else tf.keras.layers.BatchNormalization)
self._norm_with_quantize = helper.BatchNormalizationQuantized(
norm_layer)
self._norm = helper.BatchNormalizationNoQuantized(norm_layer)
if tf.keras.backend.image_data_format() == 'channels_last':
self._bn_axis = -1
else:
self._bn_axis = 1
self._bn_trainable = bn_trainable
def __init__(self,
in_filters,
out_filters,
expand_ratio,
strides,
kernel_size=3,
se_ratio=None,
stochastic_depth_drop_rate=None,
kernel_initializer='VarianceScaling',
kernel_regularizer=None,
bias_regularizer=None,
activation='relu',
se_inner_activation='relu',
se_gating_activation='sigmoid',
se_round_down_protect=True,
expand_se_in_filters=False,
depthwise_activation=None,
use_sync_bn=False,
dilation_rate=1,
divisible_by=1,
regularize_depthwise=False,
use_depthwise=True,
use_residual=True,
norm_momentum=0.99,
norm_epsilon=0.001,
output_intermediate_endpoints=False,
**kwargs):
"""Initializes an inverted bottleneck block with BN after convolutions.
Args:
in_filters: An `int` number of filters of the input tensor.
out_filters: An `int` number of filters of the output tensor.
expand_ratio: An `int` of expand_ratio for an inverted bottleneck block.
strides: An `int` block stride. If greater than 1, this block will
ultimately downsample the input.
kernel_size: An `int` kernel_size of the depthwise conv layer.
se_ratio: A `float` or None. If not None, se ratio for the squeeze and
excitation layer.
stochastic_depth_drop_rate: A `float` or None. if not None, drop rate for
the stochastic depth layer.
kernel_initializer: A `str` of kernel_initializer for convolutional
layers.
kernel_regularizer: A `tf.keras.regularizers.Regularizer` object for
Conv2D. Default to None.
bias_regularizer: A `tf.keras.regularizers.Regularizer` object for Conv2d.
Default to None.
activation: A `str` name of the activation function.
se_inner_activation: A `str` name of squeeze-excitation inner activation.
se_gating_activation: A `str` name of squeeze-excitation gating
activation.
se_round_down_protect: A `bool` of whether round down more than 10% will
be allowed in SE layer.
expand_se_in_filters: A `bool` of whether or not to expand in_filter in
squeeze and excitation layer.
depthwise_activation: A `str` name of the activation function for
depthwise only.
use_sync_bn: A `bool`. If True, use synchronized batch normalization.
dilation_rate: An `int` that specifies the dilation rate to use for.
divisible_by: An `int` that ensures all inner dimensions are divisible by
this number.
dilated convolution: An `int` to specify the same value for all spatial
dimensions.
regularize_depthwise: A `bool` of whether or not apply regularization on
depthwise.
use_depthwise: A `bool` of whether to uses fused convolutions instead of
depthwise.
use_residual: A `bool` of whether to include residual connection between
input and output.
norm_momentum: A `float` of normalization momentum for the moving average.
norm_epsilon: A `float` added to variance to avoid dividing by zero.
output_intermediate_endpoints: A `bool` of whether or not output the
intermediate endpoints.
**kwargs: Additional keyword arguments to be passed.
"""
super(InvertedBottleneckBlockQuantized, self).__init__(**kwargs)
self._in_filters = in_filters
self._out_filters = out_filters
self._expand_ratio = expand_ratio
self._strides = strides
self._kernel_size = kernel_size
self._se_ratio = se_ratio
self._divisible_by = divisible_by
self._stochastic_depth_drop_rate = stochastic_depth_drop_rate
self._dilation_rate = dilation_rate
self._use_sync_bn = use_sync_bn
self._regularize_depthwise = regularize_depthwise
self._use_depthwise = use_depthwise
self._use_residual = use_residual
self._activation = activation
self._se_inner_activation = se_inner_activation
self._se_gating_activation = se_gating_activation
self._se_round_down_protect = se_round_down_protect
self._depthwise_activation = depthwise_activation
self._kernel_initializer = kernel_initializer
self._norm_momentum = norm_momentum
self._norm_epsilon = norm_epsilon
self._kernel_regularizer = kernel_regularizer
self._bias_regularizer = bias_regularizer
self._expand_se_in_filters = expand_se_in_filters
self._output_intermediate_endpoints = output_intermediate_endpoints
norm_layer = (tf.keras.layers.experimental.SyncBatchNormalization
if use_sync_bn else tf.keras.layers.BatchNormalization)
self._norm_with_quantize = helper.BatchNormalizationQuantized(
norm_layer)
self._norm = helper.BatchNormalizationNoQuantized(norm_layer)
if tf.keras.backend.image_data_format() == 'channels_last':
self._bn_axis = -1
else:
self._bn_axis = 1
if not depthwise_activation:
self._depthwise_activation = activation
if regularize_depthwise:
self._depthsize_regularizer = kernel_regularizer
else:
self._depthsize_regularizer = None
def __init__(self,
filters: int,
kernel_size: int = 3,
strides: int = 1,
use_bias: bool = False,
use_explicit_padding: bool = False,
activation: str = 'relu6',
kernel_initializer: str = 'VarianceScaling',
kernel_regularizer: Optional[
tf.keras.regularizers.Regularizer] = None,
bias_regularizer: Optional[
tf.keras.regularizers.Regularizer] = None,
use_normalization: bool = True,
use_sync_bn: bool = False,
norm_momentum: float = 0.99,
norm_epsilon: float = 0.001,
**kwargs):
"""A convolution block with batch normalization.
Args:
filters: An `int` number of filters for the first two convolutions. Note
that the third and final convolution will use 4 times as many filters.
kernel_size: An `int` specifying the height and width of the 2D
convolution window.
strides: An `int` of block stride. If greater than 1, this block will
ultimately downsample the input.
use_bias: If True, use bias in the convolution layer.
use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
inputs so that the output dimensions are the same as if 'SAME' padding
were used.
activation: A `str` name of the activation function.
kernel_initializer: A `str` for kernel initializer of convolutional
layers.
kernel_regularizer: A `tf.keras.regularizers.Regularizer` object for
Conv2D. Default to None.
bias_regularizer: A `tf.keras.regularizers.Regularizer` object for Conv2D.
Default to None.
use_normalization: If True, use batch normalization.
use_sync_bn: If True, use synchronized batch normalization.
norm_momentum: A `float` of normalization momentum for the moving average.
norm_epsilon: A `float` added to variance to avoid dividing by zero.
**kwargs: Additional keyword arguments to be passed.
"""
super(Conv2DBNBlockQuantized, self).__init__(**kwargs)
self._filters = filters
self._kernel_size = kernel_size
self._strides = strides
self._activation = activation
self._use_bias = use_bias
self._use_explicit_padding = use_explicit_padding
self._kernel_initializer = kernel_initializer
self._kernel_regularizer = kernel_regularizer
self._bias_regularizer = bias_regularizer
self._use_normalization = use_normalization
self._use_sync_bn = use_sync_bn
self._norm_momentum = norm_momentum
self._norm_epsilon = norm_epsilon
if use_explicit_padding and kernel_size > 1:
self._padding = 'valid'
else:
self._padding = 'same'
norm_layer = (tf.keras.layers.experimental.SyncBatchNormalization
if use_sync_bn else tf.keras.layers.BatchNormalization)
self._norm_with_quantize = helper.BatchNormalizationQuantized(
norm_layer)
self._norm = helper.BatchNormalizationNoQuantized(norm_layer)
if tf.keras.backend.image_data_format() == 'channels_last':
self._bn_axis = -1
else:
self._bn_axis = 1