初窥Tensorflow Object Detection API 源码之（1.1） Resnet

Overview

resnet_v1
resnet_utilsstack_blocks_dense

bottleneck

resnet_utilsBlock

resnet_v1_50

resnet_v1_101

大名鼎鼎的Resnet众所周知，其结构我也不想太多论述，详见论文

Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

Deep Residual Learning for Image Recognition.

https://arxiv.org/abs/1512.03385

Overview

models/research/slim/nets/resnet_v1.py

resnet_v1

为resnet50，101，152，200提供总框架，blocks提供了网络结构配置

def resnet_v1(inputs,
blocks,
num_classes=None,
is_training=True,
global_pool=True,
output_stride=None,
include_root_block=True,
spatial_squeeze=True,
reuse=None,
scope=None):
with tf.variable_scope(scope, 'resnet_v1', [inputs], reuse=reuse) as sc:
end_points_collection = sc.original_name_scope + '_end_points'
with slim.arg_scope([slim.conv2d, bottleneck,
resnet_utils.stack_blocks_dense],
outputs_collections=end_points_collection):
with slim.arg_scope([slim.batch_norm], is_training=is_training):
net = inputs
if include_root_block:
if output_stride is not None:
if output_stride % 4 != 0:
raise ValueError('The output_stride needs to be a multiple of 4.')
output_stride /= 4
net = resnet_utils.conv2d_same(net, 64, 7, stride=2, scope='conv1')
net = slim.max_pool2d(net, [3, 3], stride=2, scope='pool1')
net = resnet_utils.stack_blocks_dense(net, blocks, output_stride)
# Convert end_points_collection into a dictionary of end_points.
end_points = slim.utils.convert_collection_to_dict(
end_points_collection)

if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2], name='pool5', keep_dims=True)
end_points['global_pool'] = net
if num_classes:
net = slim.conv2d(net, num_classes, [1, 1], activation_fn=None,
normalizer_fn=None, scope='logits')
end_points[sc.name + '/logits'] = net
if spatial_squeeze:
net = tf.squeeze(net, [1, 2], name='SpatialSqueeze')
end_points[sc.name + '/spatial_squeeze'] = net
end_points['predictions'] = slim.softmax(net, scope='predictions')
return net, end_points
resnet_v1.default_image_size = 224

resnet_utils.stack_blocks_dense

resnet_utils.stack_blocks_dense会解开blocks

@slim.add_arg_scope
def stack_blocks_dense(net, blocks, output_stride=None,
outputs_collections=None):
current_stride = 1

# The atrous convolution rate parameter.
rate = 1

for block in blocks:
with tf.variable_scope(block.scope, 'block', [net]) as sc:
for i, unit in enumerate(block.args):
if output_stride is not None and current_stride > output_stride:
raise ValueError('The target output_stride cannot be reached.')

with tf.variable_scope('unit_%d' % (i + 1), values=[net]):
# If we have reached the target output_stride, then we need to employ
# atrous convolution with stride=1 and multiply the atrous rate by the
# current unit's stride for use in subsequent layers.
if output_stride is not None and current_stride == output_stride:
net = block.unit_fn(net, rate=rate, **dict(unit, stride=1))
rate *= unit.get('stride', 1)

else:
net = block.unit_fn(net, rate=1, **unit)
current_stride *= unit.get('stride', 1)
net = slim.utils.collect_named_outputs(outputs_collections, sc.name, net)

if output_stride is not None and current_stride != output_stride:
raise ValueError('The target output_stride cannot be reached.')

return net

bottleneck

Resnet的核心元结构

def bottleneck(inputs,
depth,
depth_bottleneck,
stride,
rate=1,
outputs_collections=None,
scope=None,
use_bounded_activations=False):
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)
output = tf.nn.relu6(shortcut + residual)
else:
output = tf.nn.relu(shortcut + residual)

return slim.utils.collect_named_outputs(outputs_collections,
sc.name,
output)

resnet_utils.Block

class Block(collections.namedtuple('Block', ['scope', 'unit_fn', 'args'])):

Block继承了collection.namedtuple
如此，可以解开resnet_v1_block：
{
'scope':scope,
'unit_fn':bottleneck,
'args':[{
'depth':base_depth*4,
'depth_bottleneck':base_depth,
'stride':stride
}]
}

resnet_v1_50

def resnet_v1_50(inputs,
num_classes=None,
is_training=True,
global_pool=True,
output_stride=None,
spatial_squeeze=True,
reuse=None,
scope='resnet_v1_50'):
blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3', base_depth=256, num_units=6, stride=2),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1),
]
return resnet_v1(inputs, blocks, num_classes, is_training,
global_pool=global_pool, output_stride=output_stride,
include_root_block=True, spatial_squeeze=spatial_squeeze,
reuse=reuse, scope=scope)
resnet_v1_50.default_image_size = resnet_v1.default_image_size

resnet_v1_101

def resnet_v1_101(inputs,
num_classes=None,
is_training=True,
global_pool=True,
output_stride=None,
spatial_squeeze=True,
reuse=None,
scope='resnet_v1_101'):
"""ResNet-101 model of [1]. See resnet_v1() for arg and return description."""
blocks = [
resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_block('block3', base_depth=256, num_units=23, stride=2),
resnet_v1_block('block4', base_depth=512, num_units=3, stride=1),
]
return resnet_v1(inputs, blocks, num_classes, is_training,
global_pool=global_pool, output_stride=output_stride,
include_root_block=True, spatial_squeeze=spatial_squeeze,
reuse=reuse, scope=scope)
resnet_v1_101.default_image_size = resnet_v1.default_image_size

与resnet50的区别在于blocks的配置