def bottleneck(inputs, depth, depth_bottleneck, stride, rate=1,
outputs_collections=None, scope=None, attention_module=None):
"""Bottleneck residual unit variant with BN before convolutions.
This is the full preactivation residual unit variant proposed in [2]. See
Fig. 1(b) of [2] for its definition. Note that we use here the bottleneck
variant which has an extra bottleneck layer.
When putting together two consecutive ResNet blocks that use this unit, one
should use stride = 2 in the last unit of the first block.
Args:
inputs: A tensor of size [batch, height, width, channels].
depth: The depth of the ResNet unit output.
depth_bottleneck: The depth of the bottleneck layers.
stride: The ResNet unit's stride. Determines the amount of downsampling of
the units output compared to its input.
rate: An integer, rate for atrous convolution.
outputs_collections: Collection to add the ResNet unit output.
scope: Optional variable_scope.
Returns:
The ResNet unit's output.
"""
with tf.variable_scope(scope, 'bottleneck_v2', [inputs]) as sc:
depth_in = slim.utils.last_dimension(inputs.get_shape(), min_rank=4)
preact = slim.batch_norm(inputs, activation_fn=tf.nn.relu, scope='preact')
if depth == depth_in:
shortcut = resnet_utils.subsample(inputs, stride, 'shortcut')
else:
shortcut = slim.conv2d(preact, depth, [1, 1], stride=stride,
normalizer_fn=None, activation_fn=None,
scope='shortcut')
residual = slim.conv2d(preact, depth_bottleneck, [1, 1], stride=1,
scope='conv1')
residual = resnet_utils.conv2d_same(residual, depth_bottleneck, 3, stride,
rate=rate, scope='conv2')
residual = slim.conv2d(residual, depth, [1, 1], stride=1,
normalizer_fn=None, activation_fn=None,
scope='conv3')
# Add attention_module
if attention_module is not None:
residual = attach_attention_module(residual, attention_module, scope)
output = shortcut + residual
return slim.utils.collect_named_outputs(outputs_collections,
sc.name,
output)
def block35(net,
scale=1.0,
activation_fn=tf.nn.relu,
scope=None,
reuse=None,
attention_module=None):
"""Builds the 35x35 resnet block."""
with tf.variable_scope(scope, 'Block35', [net], reuse=reuse):
with tf.variable_scope('Branch_0'):
tower_conv = slim.conv2d(net, 32, 1, scope='Conv2d_1x1')
with tf.variable_scope('Branch_1'):
tower_conv1_0 = slim.conv2d(net, 32, 1, scope='Conv2d_0a_1x1')
tower_conv1_1 = slim.conv2d(tower_conv1_0,
32,
3,
scope='Conv2d_0b_3x3')
with tf.variable_scope('Branch_2'):
tower_conv2_0 = slim.conv2d(net, 32, 1, scope='Conv2d_0a_1x1')
tower_conv2_1 = slim.conv2d(tower_conv2_0,
48,
3,
scope='Conv2d_0b_3x3')
tower_conv2_2 = slim.conv2d(tower_conv2_1,
64,
3,
scope='Conv2d_0c_3x3')
mixed = tf.concat(axis=3,
values=[tower_conv, tower_conv1_1, tower_conv2_2])
up = slim.conv2d(mixed,
net.get_shape()[3],
1,
normalizer_fn=None,
activation_fn=None,
scope='Conv2d_1x1')
scaled_up = up * scale
if activation_fn == tf.nn.relu6:
# Use clip_by_value to simulate bandpass activation.
scaled_up = tf.clip_by_value(scaled_up, -6.0, 6.0)
# Add attention_module
if attention_module is not None:
scaled_up = attach_attention_module(scaled_up, attention_module,
scope)
net += scaled_up
if activation_fn:
net = activation_fn(net)
return net
def bottleneck(inputs,
depth,
depth_bottleneck,
stride,
rate=1,
outputs_collections=None,
scope=None,
use_bounded_activations=False,
attention_module=None):
"""Bottleneck residual unit variant with BN after convolutions.
This is the original residual unit proposed in [1]. See Fig. 1(a) of [2] for
its definition. Note that we use here the bottleneck variant which has an
extra bottleneck layer.
When putting together two consecutive ResNet blocks that use this unit, one
should use stride = 2 in the last unit of the first block.
Args:
inputs: A tensor of size [batch, height, width, channels].
depth: The depth of the ResNet unit output.
depth_bottleneck: The depth of the bottleneck layers.
stride: The ResNet unit's stride. Determines the amount of downsampling of
the units output compared to its input.
rate: An integer, rate for atrous convolution.
outputs_collections: Collection to add the ResNet unit output.
scope: Optional variable_scope.
use_bounded_activations: Whether or not to use bounded activations. Bounded
activations better lend themselves to quantized inference.
Returns:
The ResNet unit's output.
"""
with tf.variable_scope(scope, 'bottleneck_v1', [inputs]) as sc:
depth_in = slim.utils.last_dimension(inputs.get_shape(), min_rank=4)
if depth == depth_in:
shortcut = resnet_utils.subsample(inputs, stride, 'shortcut')
else:
shortcut = slim.conv2d(
inputs,
depth, [1, 1],
stride=stride,
activation_fn=tf.nn.relu6 if use_bounded_activations else None,
scope='shortcut')
residual = slim.conv2d(inputs, depth_bottleneck, [1, 1], stride=1,
scope='conv1')
residual = resnet_utils.conv2d_same(residual, depth_bottleneck, 3, stride,
rate=rate, scope='conv2')
residual = slim.conv2d(residual, depth, [1, 1], stride=1,
activation_fn=None, scope='conv3')
if use_bounded_activations:
# Use clip_by_value to simulate bandpass activation.
residual = tf.clip_by_value(residual, -6.0, 6.0)
# Add attention_module
if attention_module is not None:
residual = attach_attention_module(residual, attention_module, scope)
output = tf.nn.relu6(shortcut + residual)
else:
# Add attention_module
if attention_module is not None:
residual = attach_attention_module(residual, attention_module, scope)
output = tf.nn.relu(shortcut + residual)
return slim.utils.collect_named_outputs(outputs_collections,
sc.name,
output)
def inception_v4_base(inputs,
final_endpoint='Mixed_7d',
scope=None,
attention_module=None):
"""Creates the Inception V4 network up to the given final endpoint.
Args:
inputs: a 4-D tensor of size [batch_size, height, width, 3].
final_endpoint: specifies the endpoint to construct the network up to.
It can be one of [ 'Conv2d_1a_3x3', 'Conv2d_2a_3x3', 'Conv2d_2b_3x3',
'Mixed_3a', 'Mixed_4a', 'Mixed_5a', 'Mixed_5b', 'Mixed_5c', 'Mixed_5d',
'Mixed_5e', 'Mixed_6a', 'Mixed_6b', 'Mixed_6c', 'Mixed_6d', 'Mixed_6e',
'Mixed_6f', 'Mixed_6g', 'Mixed_6h', 'Mixed_7a', 'Mixed_7b', 'Mixed_7c',
'Mixed_7d']
scope: Optional variable_scope.
Returns:
logits: the logits outputs of the model.
end_points: the set of end_points from the inception model.
Raises:
ValueError: if final_endpoint is not set to one of the predefined values,
"""
end_points = {}
def add_and_check_final(name, net):
end_points[name] = net
return name == final_endpoint
with tf.variable_scope(scope, 'InceptionV4', [inputs]):
with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
stride=1,
padding='SAME'):
# 299 x 299 x 3
net = slim.conv2d(inputs,
32, [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_3x3')
if add_and_check_final('Conv2d_1a_3x3', net):
return net, end_points
# 149 x 149 x 32
net = slim.conv2d(net,
32, [3, 3],
padding='VALID',
scope='Conv2d_2a_3x3')
if add_and_check_final('Conv2d_2a_3x3', net):
return net, end_points
# 147 x 147 x 32
net = slim.conv2d(net, 64, [3, 3], scope='Conv2d_2b_3x3')
if add_and_check_final('Conv2d_2b_3x3', net):
return net, end_points
# 147 x 147 x 64
with tf.variable_scope('Mixed_3a'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.max_pool2d(net, [3, 3],
stride=2,
padding='VALID',
scope='MaxPool_0a_3x3')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net,
96, [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_0a_3x3')
net = tf.concat(axis=3, values=[branch_0, branch_1])
if add_and_check_final('Mixed_3a', net): return net, end_points
# 73 x 73 x 160
with tf.variable_scope('Mixed_4a'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net,
64, [1, 1],
scope='Conv2d_0a_1x1')
branch_0 = slim.conv2d(branch_0,
96, [3, 3],
padding='VALID',
scope='Conv2d_1a_3x3')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net,
64, [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = slim.conv2d(branch_1,
64, [1, 7],
scope='Conv2d_0b_1x7')
branch_1 = slim.conv2d(branch_1,
64, [7, 1],
scope='Conv2d_0c_7x1')
branch_1 = slim.conv2d(branch_1,
96, [3, 3],
padding='VALID',
scope='Conv2d_1a_3x3')
net = tf.concat(axis=3, values=[branch_0, branch_1])
if add_and_check_final('Mixed_4a', net): return net, end_points
# 71 x 71 x 192
with tf.variable_scope('Mixed_5a'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net,
192, [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_3x3')
with tf.variable_scope('Branch_1'):
branch_1 = slim.max_pool2d(net, [3, 3],
stride=2,
padding='VALID',
scope='MaxPool_1a_3x3')
net = tf.concat(axis=3, values=[branch_0, branch_1])
if add_and_check_final('Mixed_5a', net): return net, end_points
# 35 x 35 x 384
# 4 x Inception-A blocks
for idx in range(4):
block_scope = 'Mixed_5' + chr(ord('b') + idx)
net = block_inception_a(net, block_scope)
# Add attention_module
if attention_module is not None:
net = attach_attention_module(net, attention_module,
block_scope)
if add_and_check_final(block_scope, net):
return net, end_points
# 35 x 35 x 384
# Reduction-A block
net = block_reduction_a(net, 'Mixed_6a')
if add_and_check_final('Mixed_6a', net): return net, end_points
# 17 x 17 x 1024
# 7 x Inception-B blocks
for idx in range(7):
block_scope = 'Mixed_6' + chr(ord('b') + idx)
net = block_inception_b(net, block_scope)
# Add attention_module
if attention_module is not None:
net = attach_attention_module(net, attention_module,
block_scope)
if add_and_check_final(block_scope, net):
return net, end_points
# 17 x 17 x 1024
# Reduction-B block
net = block_reduction_b(net, 'Mixed_7a')
if add_and_check_final('Mixed_7a', net): return net, end_points
# 8 x 8 x 1536
# 3 x Inception-C blocks
for idx in range(3):
block_scope = 'Mixed_7' + chr(ord('b') + idx)
net = block_inception_c(net, block_scope)
# Add attention_module
if attention_module is not None:
net = attach_attention_module(net, attention_module,
block_scope)
if add_and_check_final(block_scope, net):
return net, end_points
raise ValueError('Unknown final endpoint %s' % final_endpoint)