Python nets.nasnet.nasnet.nasnet_large_arg_scope() Examples

The following are 30 code examples of nets.nasnet.nasnet.nasnet_large_arg_scope(). 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 nets.nasnet.nasnet , or try the search function .
Example #1
Source File: faster_rcnn_nas_feature_extractor.py    From Traffic-Rule-Violation-Detection-System with MIT License 6 votes vote down vote up 
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.
Example #2
Source File: faster_rcnn_nas_feature_extractor.py    From cartoonify with MIT License 6 votes vote down vote up 
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.
Example #3
Source File: nasnet_test.py    From edafa with MIT License 6 votes vote down vote up 
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])
Example #4
Source File: nasnet_test.py    From MAX-Object-Detector with Apache License 2.0 6 votes vote down vote up 
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])
Example #5
Source File: nasnet_test.py    From CVTron with Apache License 2.0 6 votes vote down vote up 
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])
Example #6
Source File: faster_rcnn_nas_feature_extractor.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
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.
Example #7
Source File: faster_rcnn_nas_feature_extractor.py    From MAX-Object-Detector with Apache License 2.0 6 votes vote down vote up 
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.
Example #8
Source File: nasnet_test.py    From tf-pose with Apache License 2.0 6 votes vote down vote up 
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])
Example #9
Source File: faster_rcnn_nas_feature_extractor.py    From vehicle_counting_tensorflow with MIT License 6 votes vote down vote up 
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.
Example #10
Source File: nasnet_test.py    From nasnet-tensorflow with Apache License 2.0 6 votes vote down vote up 
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])
Example #11
Source File: nasnet_test.py    From DeepLab_v3 with MIT License 6 votes vote down vote up 
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])
Example #12
Source File: faster_rcnn_nas_feature_extractor.py    From ros_people_object_detection_tensorflow with Apache License 2.0 6 votes vote down vote up 
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.
Example #13
Source File: nasnet_test.py    From SENet-tensorflow-slim with MIT License 6 votes vote down vote up 
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])
Example #14
Source File: nasnet_test.py    From yolo_v2 with Apache License 2.0 6 votes vote down vote up 
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])
Example #15
Source File: faster_rcnn_nas_feature_extractor.py    From object_detection_with_tensorflow with MIT License 6 votes vote down vote up 
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.
Example #16
Source File: faster_rcnn_nas_feature_extractor.py    From yolo_v2 with Apache License 2.0 6 votes vote down vote up 
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.
Example #17
Source File: nasnet_test.py    From CBAM-tensorflow-slim with MIT License 6 votes vote down vote up 
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])
Example #18
Source File: nasnet_test.py    From object_detection_with_tensorflow with MIT License 6 votes vote down vote up 
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])
Example #19
Source File: faster_rcnn_nas_feature_extractor.py    From object_detection_with_tensorflow with MIT License 6 votes vote down vote up 
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.
Example #20
Source File: faster_rcnn_nas_feature_extractor.py    From Elphas with Apache License 2.0 6 votes vote down vote up 
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.
Example #21
Source File: nasnet_test.py    From Gun-Detector with Apache License 2.0 6 votes vote down vote up 
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])
Example #22
Source File: faster_rcnn_nas_feature_extractor.py    From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 6 votes vote down vote up 
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.
Example #23
Source File: faster_rcnn_nas_feature_extractor.py    From Gun-Detector with Apache License 2.0 6 votes vote down vote up 
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.
Example #24
Source File: nasnet_test.py    From Creative-Adversarial-Networks with MIT License 6 votes vote down vote up 
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])
Example #25
Source File: nasnet_test.py    From TwinGAN with Apache License 2.0 6 votes vote down vote up 
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])
Example #26
Source File: faster_rcnn_nas_feature_extractor.py    From ros_tensorflow with Apache License 2.0 6 votes vote down vote up 
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.
Example #27
Source File: nasnet_test.py    From BMW-TensorFlow-Training-GUI with Apache License 2.0 6 votes vote down vote up 
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])
Example #28
Source File: nasnet_test.py    From style_swap_tensorflow with Apache License 2.0 6 votes vote down vote up 
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])
Example #29
Source File: faster_rcnn_nas_feature_extractor.py    From BMW-TensorFlow-Training-GUI with Apache License 2.0 6 votes vote down vote up 
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.
Example #30
Source File: nasnet_test.py    From MAX-Image-Segmenter with Apache License 2.0 6 votes vote down vote up 
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])