def _conv_block(inp, convs, do_skip=True):
x = inp
count = 0
for conv in convs:
if count == (len(convs) - 2) and do_skip:
skip_connection = x
count += 1
if conv['stride'] > 1:
x = ZeroPadding2D(((1, 0), (1, 0)))(
x) # unlike tensorflow darknet prefer left and top paddings
x = Conv2D(
conv['filter'],
conv['kernel'],
strides=conv['stride'],
padding='valid' if conv['stride'] > 1 else
'same', # unlike tensorflow darknet prefer left and top paddings
name='conv_' + str(conv['layer_idx']),
use_bias=False if conv['bnorm'] else True)(x)
if conv['bnorm']:
x = BatchNormalization(epsilon=0.001,
name='bnorm_' + str(conv['layer_idx']))(x)
if conv['leaky']:
x = LeakyReLU(alpha=0.1, name='leaky_' + str(conv['layer_idx']))(x)
return add([skip_connection, x]) if do_skip else x
def residual_block(
inputs,
num_filters=16,
kernel_size=3,
strides=1,
activation="relu",
batch_normalization=True,
conv_first=True,
):
"""2D Convolution-Batch Normalization-Activation stack builder
# Arguments
inputs (tensor): input tensor from input image or previous layer
num_filters (int): Conv2D number of filters
kernel_size (int): Conv2D square kernel dimensions
strides (int): Conv2D square stride dimensions
activation (string): activation name
batch_normalization (bool): whether to include batch normalization
conv_first (bool): conv-bn-activation (True) or
bn-activation-conv (False)
# Returns
x (tensor): tensor as input to the next layer
"""
conv = Conv2D(
num_filters,
kernel_size=kernel_size,
strides=strides,
padding="same",
kernel_initializer="he_normal",
kernel_regularizer=l2(1e-4),
activation=None,
)
conv2 = Conv2D(
num_filters,
kernel_size=kernel_size,
strides=strides,
padding="same",
kernel_initializer="he_normal",
kernel_regularizer=l2(1e-4),
activation="linear",
)
x = conv(inputs)
x = BatchNormalization()(x)
x = Activation(activation)(x)
x = conv2(x)
x = add([inputs, x])
x = BatchNormalization()(x)
x = Activation(activation)(x)
return x
def _shortcut3d(input, residual):
"""3D shortcut to match input and residual and merges them with "sum"."""
stride_dim1 = ceil(input.get_shape().as_list()[DIM1_AXIS] \
/ residual.get_shape().as_list()[DIM1_AXIS])
stride_dim2 = ceil(input.get_shape().as_list()[DIM2_AXIS] \
/ residual.get_shape().as_list()[DIM2_AXIS])
stride_dim3 = ceil(input.get_shape().as_list()[DIM3_AXIS] \
/ residual.get_shape().as_list()[DIM3_AXIS])
equal_channels = residual.get_shape().as_list()[CHANNEL_AXIS] \
== input.get_shape().as_list()[CHANNEL_AXIS]
shortcut = input
if stride_dim1 > 1 or stride_dim2 > 1 or stride_dim3 > 1 \
or not equal_channels:
shortcut = Conv3D(
filters=residual.get_shape().as_list()[CHANNEL_AXIS],
kernel_size=(1, 1, 1),
strides=(stride_dim1, stride_dim2, stride_dim3),
kernel_initializer="he_normal", padding="valid",
kernel_regularizer=l2(1e-4)
)(input)
return add([shortcut, residual])
def identity_block_base(input_tensor,
kernel_size,
filters,
stage,
block,
num_updates,
dropout_rate=0.,
use_variational_layers=False):
"""The identity block is the block that has no conv layer at shortcut.
Arguments:
input_tensor: input tensor
kernel_size: default 3, the kernel size of
middle conv layer at main path
filters: list of integers, the filters of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
num_updates: integer, total steps in an epoch (for weighting the loss)
dropout_rate: float, always-on dropout rate.
use_variational_layers: boolean, if true train a variational model
Returns:
x: Output tensor for the block.
"""
filters1, filters2, filters3 = filters
divergence_fn = lambda q, p, ignore: (tfd.kl_divergence(q, p) / num_updates
)
if backend.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
if not use_variational_layers:
first_conv_2d = layers.Conv2D(
filters1, (1, 1),
use_bias=False,
kernel_initializer='he_normal',
kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
name=conv_name_base + '2a')
if dropout_rate > 0.:
x = layers.Dropout(dropout_rate)(input_tensor, training=True)
x = first_conv_2d(x)
else:
x = first_conv_2d(input_tensor)
x = layers.BatchNormalization(axis=bn_axis,
momentum=BATCH_NORM_DECAY,
epsilon=BATCH_NORM_EPSILON,
name=bn_name_base + '2a')(x)
x = layers.Activation('relu')(x)
if dropout_rate > 0.:
x = layers.Dropout(dropout_rate)(x, training=True)
x = layers.Conv2D(filters2,
kernel_size,
use_bias=False,
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
name=conv_name_base + '2b')(x)
x = layers.BatchNormalization(axis=bn_axis,
momentum=BATCH_NORM_DECAY,
epsilon=BATCH_NORM_EPSILON,
name=bn_name_base + '2b')(x)
x = layers.Activation('relu')(x)
if dropout_rate > 0.:
x = layers.Dropout(dropout_rate)(x, training=True)
x = layers.Conv2D(filters3, (1, 1),
use_bias=False,
kernel_initializer='he_normal',
kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
name=conv_name_base + '2c')(x)
x = layers.BatchNormalization(axis=bn_axis,
momentum=BATCH_NORM_DECAY,
epsilon=BATCH_NORM_EPSILON,
name=bn_name_base + '2c')(x)
else:
x = tfpl.Convolution2DFlipout(
filters1,
kernel_size=(1, 1),
padding='SAME',
name=conv_name_base + '2a',
kernel_divergence_fn=divergence_fn,
)(input_tensor)
x = layers.BatchNormalization(axis=bn_axis,
momentum=BATCH_NORM_DECAY,
epsilon=BATCH_NORM_EPSILON,
name=bn_name_base + '2a')(x)
x = layers.Activation('relu')(x)
x = tfpl.Convolution2DFlipout(
filters2,
kernel_size=kernel_size,
padding='SAME',
activation=None,
name=conv_name_base + '2b',
kernel_divergence_fn=divergence_fn,
)(x)
x = layers.BatchNormalization(axis=bn_axis,
momentum=BATCH_NORM_DECAY,
epsilon=BATCH_NORM_EPSILON,
name=bn_name_base + '2b')(x)
x = layers.Activation('relu')(x)
x = tfpl.Convolution2DFlipout(
filters3,
kernel_size=(1, 1),
padding='SAME',
activation=None,
name=conv_name_base + '2c',
kernel_divergence_fn=divergence_fn,
)(x)
x = layers.BatchNormalization(axis=bn_axis,
momentum=BATCH_NORM_DECAY,
epsilon=BATCH_NORM_EPSILON,
name=bn_name_base + '2c')(x)
x = layers.add([x, input_tensor])
x = layers.Activation('relu')(x)
return x
def inner(x):
for i in range(n):
x2 = conv(channels * k, strides if i == 0 else 1)(x)
x = add([resize(x, K.int_shape(x2)), x2])
return x
