Python源码示例：nets.nasnet.nasnet.nasnet_large_arg_scope()
示例1
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例2
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例3
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例4
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例5
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例6
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例7
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例8
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例9
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例10
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例11
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例12
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例13
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例14
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例15
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例16
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例17
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例18
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例19
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例20
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例21
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例22
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例23
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例24
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例25
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例26
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例27
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例28
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
示例29
def nasnet_large_arg_scope_for_detection(is_batch_norm_training=False):
"""Defines the default arg scope for the NASNet-A Large for object detection.
This provides a small edit to switch batch norm training on and off.
Args:
is_batch_norm_training: Boolean indicating whether to train with batch norm.
Returns:
An `arg_scope` to use for the NASNet Large Model.
"""
imagenet_scope = nasnet.nasnet_large_arg_scope()
with arg_scope(imagenet_scope):
with arg_scope([slim.batch_norm], is_training=is_batch_norm_training) as sc:
return sc
# Note: This is largely a copy of _build_nasnet_base inside nasnet.py but
# with special edits to remove instantiation of the stem and the special
# ability to receive as input a pair of hidden states.
示例30
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
