def _build_tail(self, inputs, is_training=False):
if not self._use_tail:
return inputs
if self._architecture == 'resnet_v1_101':
train_batch_norm = (is_training
and self._config.get('train_batch_norm'))
with self._enter_variable_scope():
weight_decay = (self._config.get('arg_scope',
{}).get('weight_decay', 0))
with tf.variable_scope(self._architecture, reuse=True):
resnet_arg_scope = resnet_utils.resnet_arg_scope(
batch_norm_epsilon=1e-5,
batch_norm_scale=True,
weight_decay=weight_decay)
with slim.arg_scope(resnet_arg_scope):
with slim.arg_scope([slim.batch_norm],
is_training=train_batch_norm):
blocks = [
resnet_utils.Block('block4',
resnet_v1.bottleneck,
[{
'depth': 2048,
'depth_bottleneck': 512,
'stride': 1
}] * 3)
]
proposal_classifier_features = (
resnet_utils.stack_blocks_dense(
inputs, blocks))
else:
proposal_classifier_features = inputs
return proposal_classifier_features
def _resnet_plain(self, inputs, blocks, output_stride=None, scope=None):
"""A plain ResNet without extra layers before or after the ResNet blocks."""
with tf.variable_scope(scope, values=[inputs]):
with slim.arg_scope([slim.conv2d], outputs_collections='end_points'):
net = resnet_utils.stack_blocks_dense(inputs, blocks, output_stride)
end_points = slim.utils.convert_collection_to_dict('end_points')
return net, end_points
def _extract_box_classifier_features(self, proposal_feature_maps, scope):
"""Extracts second stage box classifier features.
Args:
proposal_feature_maps: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, crop_height, crop_width, depth]
representing the feature map cropped to each proposal.
scope: A scope name (unused).
Returns:
proposal_classifier_features: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, height, width, depth]
representing box classifier features for each proposal.
"""
with tf.variable_scope(self._architecture, reuse=self._reuse_weights):
with slim.arg_scope(
resnet_utils.resnet_arg_scope(
batch_norm_epsilon=1e-5,
batch_norm_scale=True,
weight_decay=self._weight_decay)):
with slim.arg_scope([slim.batch_norm],
is_training=self._train_batch_norm):
blocks = [
resnet_utils.Block('block4', resnet_v1.bottleneck,
[{
'depth': 2048,
'depth_bottleneck': 512,
'stride': 1
}] * 3)
]
proposal_classifier_features = resnet_utils.stack_blocks_dense(
proposal_feature_maps, blocks)
return proposal_classifier_features
def _resnet_plain(self, inputs, blocks, output_stride=None, scope=None):
"""A plain ResNet without extra layers before or after the ResNet blocks."""
with tf.variable_scope(scope, values=[inputs]):
with slim.arg_scope([slim.conv2d], outputs_collections='end_points'):
net = resnet_utils.stack_blocks_dense(inputs, blocks, output_stride)
end_points = dict(tf.get_collection('end_points'))
return net, end_points
def resnet_v1(inputs,
blocks,
filter_scale=1.0,
num_classes=None,
is_training=True,
global_pool=True,
output_stride=None,
include_root_block=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 // filter_scale,
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)
if global_pool:
# Global average pooling.
net = math_ops.reduce_mean(net, [1, 2],
name='pool5',
keepdims=True)
if num_classes is not None:
net = slim.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='logits')
# Convert end_points_collection into a dictionary of end_points.
end_points = slim.utils.convert_collection_to_dict(
end_points_collection)
if num_classes is not None:
end_points['predictions'] = slim.softmax(
net, scope='predictions')
return net, end_points
def _atrousValues(self, bottleneck):
"""Verify the values of dense feature extraction by atrous convolution.
Make sure that dense feature extraction by stack_blocks_dense() followed by
subsampling gives identical results to feature extraction at the nominal
network output stride using the simple self._stack_blocks_nondense() above.
Args:
bottleneck: The bottleneck function.
"""
blocks = [
resnet_utils.Block('block1', bottleneck, [(4, 1, 1), (4, 1, 2)]),
resnet_utils.Block('block2', bottleneck, [(8, 2, 1), (8, 2, 2)]),
resnet_utils.Block('block3', bottleneck, [(16, 4, 1), (16, 4, 2)]),
resnet_utils.Block('block4', bottleneck, [(32, 8, 1), (32, 8, 1)])
]
nominal_stride = 8
# Test both odd and even input dimensions.
height = 30
width = 31
with slim.arg_scope(resnet_utils.resnet_arg_scope(is_training=False)):
for output_stride in [1, 2, 4, 8, None]:
with tf.Graph().as_default():
with self.test_session() as sess:
tf.set_random_seed(0)
inputs = create_test_input(1, height, width, 3)
# Dense feature extraction followed by subsampling.
output = resnet_utils.stack_blocks_dense(
inputs, blocks, output_stride)
if output_stride is None:
factor = 1
else:
factor = nominal_stride // output_stride
output = resnet_utils.subsample(output, factor)
# Make the two networks use the same weights.
tf.get_variable_scope().reuse_variables()
# Feature extraction at the nominal network rate.
expected = self._stack_blocks_nondense(inputs, blocks)
sess.run(tf.initialize_all_variables())
output, expected = sess.run([output, expected])
self.assertAllClose(output,
expected,
atol=1e-4,
rtol=1e-4)
def _atrousValues(self, bottleneck):
"""Verify the values of dense feature extraction by atrous convolution.
Make sure that dense feature extraction by stack_blocks_dense() followed by
subsampling gives identical results to feature extraction at the nominal
network output stride using the simple self._stack_blocks_nondense() above.
Args:
bottleneck: The bottleneck function.
"""
blocks = [
resnet_utils.Block('block1', bottleneck, [(4, 1, 1), (4, 1, 2)]),
resnet_utils.Block('block2', bottleneck, [(8, 2, 1), (8, 2, 2)]),
resnet_utils.Block('block3', bottleneck, [(16, 4, 1), (16, 4, 2)]),
resnet_utils.Block('block4', bottleneck, [(32, 8, 1), (32, 8, 1)])
]
nominal_stride = 8
# Test both odd and even input dimensions.
height = 30
width = 31
with slim.arg_scope(resnet_utils.resnet_arg_scope(is_training=False)):
for output_stride in [1, 2, 4, 8, None]:
with tf.Graph().as_default():
with self.test_session() as sess:
tf.set_random_seed(0)
inputs = create_test_input(1, height, width, 3)
# Dense feature extraction followed by subsampling.
output = resnet_utils.stack_blocks_dense(inputs,
blocks,
output_stride)
if output_stride is None:
factor = 1
else:
factor = nominal_stride // output_stride
output = resnet_utils.subsample(output, factor)
# Make the two networks use the same weights.
tf.get_variable_scope().reuse_variables()
# Feature extraction at the nominal network rate.
expected = self._stack_blocks_nondense(inputs, blocks)
sess.run(tf.global_variables_initializer())
output, expected = sess.run([output, expected])
self.assertAllClose(output, expected, atol=1e-4, rtol=1e-4)
def _build_tail(self, inputs, is_training=False):
if not self._use_tail:
return inputs
if self._architecture == 'resnet_v1_101':
train_batch_norm = (
is_training and self._config.get('train_batch_norm')
)
with self._enter_variable_scope():
weight_decay = (
self._config.get('arg_scope', {}).get('weight_decay', 0)
)
with tf.variable_scope(self._architecture, reuse=True):
resnet_arg_scope = resnet_utils.resnet_arg_scope(
batch_norm_epsilon=1e-5,
batch_norm_scale=True,
weight_decay=weight_decay
)
with slim.arg_scope(resnet_arg_scope):
with slim.arg_scope(
[slim.batch_norm], is_training=train_batch_norm
):
blocks = [
resnet_utils.Block(
'block4',
resnet_v1.bottleneck,
[{
'depth': 2048,
'depth_bottleneck': 512,
'stride': 1
}] * 3
)
]
proposal_classifier_features = (
resnet_utils.stack_blocks_dense(inputs, blocks)
)
else:
proposal_classifier_features = inputs
return proposal_classifier_features
def resnet_rcnn(features, num_classes):
resnet_arg_scope = resnet_utils.resnet_arg_scope(batch_norm_epsilon=1e-5,
batch_norm_scale=True,
weight_decay=5e-4)
with slim.arg_scope(resnet_arg_scope):
with slim.arg_scope([slim.batch_norm], is_training=True):
blocks = [
resnet_utils.Block('block4', resnet_v1.bottleneck,
[{
'depth': 2048,
'depth_bottleneck': 512,
'stride': 1
}] * 3)
]
net = resnet_utils.stack_blocks_dense(features, blocks)
flat = tf.layers.flatten(net)
cls_score = tf.layers.dense(flat, units=(num_classes + 1))
reg_score = tf.layers.dense(flat, units=(num_classes * 4))
cls_probs = tf.nn.softmax(cls_score)
return cls_score, cls_probs, reg_score
def _build_tail(self, inputs, is_training=False):
if not self._use_tail:
return inputs
if self._architecture == "resnet_v1_101":
train_batch_norm = is_training and self._config.get(
"train_batch_norm")
with self._enter_variable_scope():
weight_decay = self._config.get("arg_scope",
{}).get("weight_decay", 0)
with tf.variable_scope(self._architecture, reuse=True):
resnet_arg_scope = resnet_utils.resnet_arg_scope(
batch_norm_epsilon=1e-5,
batch_norm_scale=True,
weight_decay=weight_decay,
)
with slim.arg_scope(resnet_arg_scope):
with slim.arg_scope([slim.batch_norm],
is_training=train_batch_norm):
blocks = [
resnet_utils.Block(
"block4",
resnet_v1.bottleneck,
[{
"depth": 2048,
"depth_bottleneck": 512,
"stride": 1,
}] * 3,
)
]
proposal_classifier_features = (
resnet_utils.stack_blocks_dense(
inputs, blocks))
else:
proposal_classifier_features = inputs
return proposal_classifier_features
def resnet_v1_beta(inputs,
blocks,
num_classes=None,
is_training=None,
global_pool=True,
output_stride=None,
root_block_fn=None,
reuse=None,
scope=None):
"""Generator for v1 ResNet models (beta variant).
This function generates a family of modified ResNet v1 models. In particular,
the first original 7x7 convolution is replaced with three 3x3 convolutions.
See the resnet_v1_*() methods for specific model instantiations, obtained by
selecting different block instantiations that produce ResNets of various
depths.
The code is modified from slim/nets/resnet_v1.py, and please refer to it for
more details.
Args:
inputs: A tensor of size [batch, height_in, width_in, channels].
blocks: A list of length equal to the number of ResNet blocks. Each element
is a resnet_utils.Block object describing the units in the block.
num_classes: Number of predicted classes for classification tasks. If None
we return the features before the logit layer.
is_training: Enable/disable is_training for batch normalization.
global_pool: If True, we perform global average pooling before computing the
logits. Set to True for image classification, False for dense prediction.
output_stride: If None, then the output will be computed at the nominal
network stride. If output_stride is not None, it specifies the requested
ratio of input to output spatial resolution.
root_block_fn: The function consisting of convolution operations applied to
the root input. If root_block_fn is None, use the original setting of
RseNet-v1, which is simply one convolution with 7x7 kernel and stride=2.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
Returns:
net: A rank-4 tensor of size [batch, height_out, width_out, channels_out].
If global_pool is False, then height_out and width_out are reduced by a
factor of output_stride compared to the respective height_in and width_in,
else both height_out and width_out equal one. If num_classes is None, then
net is the output of the last ResNet block, potentially after global
average pooling. If num_classes is not None, net contains the pre-softmax
activations.
end_points: A dictionary from components of the network to the corresponding
activation.
Raises:
ValueError: If the target output_stride is not valid.
"""
if root_block_fn is None:
root_block_fn = functools.partial(resnet_utils.conv2d_same,
num_outputs=64,
kernel_size=7,
stride=2,
scope='conv1')
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):
if is_training is not None:
arg_scope = slim.arg_scope([slim.batch_norm],
is_training=is_training)
else:
arg_scope = slim.arg_scope([])
with arg_scope:
net = inputs
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 = root_block_fn(net) # (N, 375, 375, 128)
net = slim.max_pool2d(net,
3,
stride=2,
padding='SAME',
scope='pool1') # (N, 188, 188, 128)
net = resnet_utils.stack_blocks_dense(
net, blocks, output_stride) # (N, 94, 94, 2048)
if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2],
name='pool5',
keepdims=True)
if num_classes is not None:
net = slim.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='logits')
# Convert end_points_collection into a dictionary of end_points.
end_points = slim.utils.convert_collection_to_dict(
end_points_collection)
if num_classes is not None:
end_points['predictions'] = slim.softmax(
net, scope='predictions')
return net, end_points
def resnet_v1(inputs,
blocks,
num_classes=None,
global_pool=True,
output_stride=None,
include_root_block=True,
reuse=None,
scope=None):
"""Generator for v1 ResNet models.
This function generates a family of ResNet v1 models. See the resnet_v1_*()
methods for specific model instantiations, obtained by selecting different
block instantiations that produce ResNets of various depths.
Training for image classification on Imagenet is usually done with [224, 224]
inputs, resulting in [7, 7] feature maps at the output of the last ResNet
block for the ResNets defined in [1] that have nominal stride equal to 32.
However, for dense prediction tasks we advise that one uses inputs with
spatial dimensions that are multiples of 32 plus 1, e.g., [321, 321]. In
this case the feature maps at the ResNet output will have spatial shape
[(height - 1) / output_stride + 1, (width - 1) / output_stride + 1]
and corners exactly aligned with the input image corners, which greatly
facilitates alignment of the features to the image. Using as input [225, 225]
images results in [8, 8] feature maps at the output of the last ResNet block.
For dense prediction tasks, the ResNet needs to run in fully-convolutional
(FCN) mode and global_pool needs to be set to False. The ResNets in [1, 2] all
have nominal stride equal to 32 and a good choice in FCN mode is to use
output_stride=16 in order to increase the density of the computed features at
small computational and memory overhead, cf. http://arxiv.org/abs/1606.00915.
Args:
inputs: A tensor of size [batch, height_in, width_in, channels].
blocks: A list of length equal to the number of ResNet blocks. Each element
is a resnet_utils.Block object describing the units in the block.
num_classes: Number of predicted classes for classification tasks. If None
we return the features before the logit layer.
global_pool: If True, we perform global average pooling before computing the
logits. Set to True for image classification, False for dense prediction.
output_stride: If None, then the output will be computed at the nominal
network stride. If output_stride is not None, it specifies the requested
ratio of input to output spatial resolution.
include_root_block: If True, include the initial convolution followed by
max-pooling, if False excludes it.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
Returns:
net: A rank-4 tensor of size [batch, height_out, width_out, channels_out].
If global_pool is False, then height_out and width_out are reduced by a
factor of output_stride compared to the respective height_in and width_in,
else both height_out and width_out equal one. If num_classes is None, then
net is the output of the last ResNet block, potentially after global
average pooling. If num_classes is not None, net contains the pre-softmax
activations.
end_points: A dictionary from components of the network to the corresponding
activation.
Raises:
ValueError: If the target output_stride is not valid.
"""
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):
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)
if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2], name='pool5', keep_dims=True)
if num_classes is not None:
net = slim.conv2d(net, num_classes, [1, 1], activation_fn=None,
normalizer_fn=None, scope='logits')
# Convert end_points_collection into a dictionary of end_points.
end_points = slim.utils.convert_collection_to_dict(end_points_collection)
if num_classes is not None:
end_points['predictions'] = slim.softmax(net, scope='predictions')
return net, end_points
def resnet_v1_beta(inputs,
blocks,
num_classes=None,
is_training=None,
global_pool=True,
output_stride=None,
root_block_fn=None,
reuse=None,
scope=None):
"""V1 ResNet模型的生成器
这个函数生成一系列经过修改的ResNet v1模型。 特别是，第一个原始7x7卷积被三个3x3卷积替换。
有关特定模型实例的信息，请参阅resnet_v1 _ *（）方法，这些方法是通过选择生成不同深度ResNets的不同块实例来获得的。
:param inputs:tensor,[batch, height_in, width_in, channels]
:param blocks:长度等于ResNet块数的列表。 每个元素都是一个resnet_utils.Block对象，用于描述块中的单位。
:param num_classes:用于分类任务的预测类数。如果为None在最后的回归层返回特征
:param is_training:是否用批正则化
:param global_pool:如果为True,在计算回归之前使用全局平均池化。设置为真用于图像分类,假则用于密集预测。
:param output_stride:如果为None，则输出将在标称网络步长处计算。 如果output_stride不是None，则它指定所请求的输入与输出空间分辨率的比率。
:param root_block_fn:该函数由应用于根输入的卷积运算组成。 如果root_block_fn为None，
则使用RseNet-v1的原始设置，该设置只是一个带有7x7内核和stride = 2的卷积。
:param reuse:是否应该重用网络及其变量。 重用的话，必须给定重用的'scope'
:param scope:可选variable_scope
:return:nets.等级-4张量的大小[batch，height_out，width_out，channels_out]。 如果global_pool为False，
则height_out和width_out与相应的height_in和width_in相比减少了output_stride因子，
否则height_out和width_out都等于1。 如果num_classes为None，则net是最后一个ResNet块的输出，可能是在全局平均池之后。
如果num_classes不是None，则net包含pre-softmax激活。
end_points: 从网络组件到相应激活的字典。
:raise:如果目标输出步长无效则
"""
if root_block_fn is None:
root_block_fn = functools.partial(resnet_utils.conv2d_same,
num_outputs=64,
kernel_size=7,
stride=2,
scope='conv1')
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):
if is_training is not None:
arg_scope = slim.arg_scope([slim.batch_norm],
is_training=is_training)
else:
arg_scope = slim.arg_scope([])
with arg_scope:
net = inputs
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 = root_block_fn(net)
net = slim.max_pool2d(net,
3,
stride=2,
padding='SAME',
scope='pool1')
net = resnet_utils.stack_blocks_dense(net, blocks,
output_stride)
if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2],
name='pool5',
keepdims=True)
if num_classes is not None:
net = slim.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='logits')
# Convert end_points_collection into a dictionary of end_points.
end_points = slim.utils.convert_collection_to_dict(
end_points_collection)
if num_classes is not None:
end_points['predictions'] = slim.softmax(
net, scope='predictions')
return net, end_points
def resnet_v1_beta(inputs,
blocks,
num_classes=None,
is_training=None,
global_pool=True,
output_stride=None,
root_block_fn=None,
reuse=None,
scope=None):
"""Generator for v1 ResNet models (beta variant).
This function generates a family of modified ResNet v1 models. In particular,
the first original 7x7 convolution is replaced with three 3x3 convolutions.
See the resnet_v1_*() methods for specific model instantiations, obtained by
selecting different block instantiations that produce ResNets of various
depths.
The code is modified from slim/nets/resnet_v1.py, and please refer to it for
more details.
Args:
inputs: A tensor of size [batch, height_in, width_in, channels].
blocks: A list of length equal to the number of ResNet blocks. Each element
is a resnet_utils.Block object describing the units in the block.
num_classes: Number of predicted classes for classification tasks. If None
we return the features before the logit layer.
is_training: Enable/disable is_training for batch normalization.
global_pool: If True, we perform global average pooling before computing the
logits. Set to True for image classification, False for dense prediction.
output_stride: If None, then the output will be computed at the nominal
network stride. If output_stride is not None, it specifies the requested
ratio of input to output spatial resolution.
root_block_fn: The function consisting of convolution operations applied to
the root input. If root_block_fn is None, use the original setting of
RseNet-v1, which is simply one convolution with 7x7 kernel and stride=2.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
Returns:
net: A rank-4 tensor of size [batch, height_out, width_out, channels_out].
If global_pool is False, then height_out and width_out are reduced by a
factor of output_stride compared to the respective height_in and width_in,
else both height_out and width_out equal one. If num_classes is None, then
net is the output of the last ResNet block, potentially after global
average pooling. If num_classes is not None, net contains the pre-softmax
activations.
end_points: A dictionary from components of the network to the corresponding
activation.
Raises:
ValueError: If the target output_stride is not valid.
"""
if root_block_fn is None:
root_block_fn = functools.partial(resnet_utils.conv2d_same,
num_outputs=64,
kernel_size=7,
stride=2,
scope='conv1')
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):
if is_training is not None:
arg_scope = slim.arg_scope([slim.batch_norm], is_training=is_training)
else:
arg_scope = slim.arg_scope([])
with arg_scope:
net = inputs
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 = root_block_fn(net)
net = slim.max_pool2d(net, 3, stride=2, padding='SAME', scope='pool1')
net = resnet_utils.stack_blocks_dense(net, blocks, output_stride)
if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2], name='pool5', keepdims=True)
if num_classes is not None:
net = slim.conv2d(net, num_classes, [1, 1], activation_fn=None,
normalizer_fn=None, scope='logits')
# Convert end_points_collection into a dictionary of end_points.
end_points = slim.utils.convert_collection_to_dict(
end_points_collection)
if num_classes is not None:
end_points['predictions'] = slim.softmax(net, scope='predictions')
return net, end_points
def resnet_v2(inputs,
blocks,
blocks2,
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_v2', [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
# We do not include batch normalization or activation functions in
# conv1 because the first ResNet unit will perform these. Cf.
# Appendix of [2].
with slim.arg_scope([slim.conv2d],
activation_fn=None,
normalizer_fn=None):
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)
#net = resnet_utils.stack_blocks_dense(net, blocks[:-2], output_stride)
CONV4 = net
Gap4 = tf.reduce_mean(net, [1, 2],
name='pool_gp',
keep_dims=True)
net = resnet_utils.stack_blocks_dense(net, blocks2,
output_stride)
# This is needed because the pre-activation variant does not have batch
# normalization or activation functions in the residual unit output. See
# Appendix of [2].
net = slim.batch_norm(net,
activation_fn=tf.nn.relu,
scope='postnorm')
# 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.
SPATIAL = net
net = tf.reduce_mean(net, [1, 2],
name='pool5',
keep_dims=True)
Gap = net
end_points['global_pool'] = net
if num_classes is not None:
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 Gap, CONV4, net, end_points
return Gap, SPATIAL, net, end_points
