Python tensorflow.contrib.slim.nets.resnet_utils.stack_blocks_dense() Examples
The following are 7
code examples of tensorflow.contrib.slim.nets.resnet_utils.stack_blocks_dense().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
tensorflow.contrib.slim.nets.resnet_utils
, or try the search function
.
.
Example #1
| Source File: truncated_base_network.py From Table-Detection-using-Deep-learning with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
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
Example #2
| Source File: resnet_v2_test.py From deep_image_model with Apache License 2.0 | 5 votes |
|
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
Example #3
| Source File: resnet_v1_test.py From deep_image_model with Apache License 2.0 | 5 votes |
|
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
Example #4
| Source File: truncated_base_network.py From Tabulo with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
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
Example #5
| Source File: truncated_base_network.py From luminoth with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
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
Example #6
| Source File: resnet_v2_test.py From deep_image_model with Apache License 2.0 | 4 votes |
|
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)
Example #7
| Source File: resnet_v1_test.py From deep_image_model with Apache License 2.0 | 4 votes |
|
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)
