Python nasnet_utils.factorized_reduction方法代码示例

# 需要导入模块: from nets.nasnet import nasnet_utils [as 别名]
# 或者: from nets.nasnet.nasnet_utils import factorized_reduction [as 别名]
def build_nasnet_cifar(
    images, num_classes, is_training=True):
  """Build NASNet model for the Cifar Dataset."""
  hparams = _cifar_config(is_training=is_training)

  if tf.test.is_gpu_available() and hparams.data_format == 'NHWC':
    tf.logging.info('A GPU is available on the machine, consider using NCHW '
                    'data format for increased speed on GPU.')

  if hparams.data_format == 'NCHW':
    images = tf.transpose(images, [0, 3, 1, 2])

  # Calculate the total number of cells in the network
  # Add 2 for the reduction cells
  total_num_cells = hparams.num_cells + 2

  normal_cell = nasnet_utils.NasNetANormalCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  reduction_cell = nasnet_utils.NasNetAReductionCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  with arg_scope([slim.dropout, nasnet_utils.drop_path, slim.batch_norm],
                 is_training=is_training):
    with arg_scope([slim.avg_pool2d,
                    slim.max_pool2d,
                    slim.conv2d,
                    slim.batch_norm,
                    slim.separable_conv2d,
                    nasnet_utils.factorized_reduction,
                    nasnet_utils.global_avg_pool,
                    nasnet_utils.get_channel_index,
                    nasnet_utils.get_channel_dim],
                   data_format=hparams.data_format):
      return _build_nasnet_base(images,
                                normal_cell=normal_cell,
                                reduction_cell=reduction_cell,
                                num_classes=num_classes,
                                hparams=hparams,
                                is_training=is_training,
                                stem_type='cifar') 

# 需要导入模块: from nets.nasnet import nasnet_utils [as 别名]
# 或者: from nets.nasnet.nasnet_utils import factorized_reduction [as 别名]
def test_factorized_reduction(self):
    data_format = 'NHWC'
    output_shape = (5, 10, 20, 16)
    inputs = tf.placeholder(tf.float32, (5, 10, 20, 10))
    output = nasnet_utils.factorized_reduction(
        inputs, 16, stride=1, data_format=data_format)
    self.assertSequenceEqual(output_shape, output.shape.as_list()) 

# 需要导入模块: from nets.nasnet import nasnet_utils [as 别名]
# 或者: from nets.nasnet.nasnet_utils import factorized_reduction [as 别名]
def build_pnasnet_large(images,
                        num_classes,
                        is_training=True,
                        final_endpoint=None,
                        config=None):
  """Build PNASNet Large model for the ImageNet Dataset."""
  hparams = copy.deepcopy(config) if config else large_imagenet_config()
  # pylint: disable=protected-access
  nasnet._update_hparams(hparams, is_training)
  # pylint: enable=protected-access

  if tf.test.is_gpu_available() and hparams.data_format == 'NHWC':
    tf.logging.info('A GPU is available on the machine, consider using NCHW '
                    'data format for increased speed on GPU.')

  if hparams.data_format == 'NCHW':
    images = tf.transpose(images, [0, 3, 1, 2])

  # Calculate the total number of cells in the network.
  # There is no distinction between reduction and normal cells in PNAS so the
  # total number of cells is equal to the number normal cells plus the number
  # of stem cells (two by default).
  total_num_cells = hparams.num_cells + 2

  normal_cell = PNasNetNormalCell(hparams.num_conv_filters,
                                  hparams.drop_path_keep_prob, total_num_cells,
                                  hparams.total_training_steps)
  with arg_scope(
      [slim.dropout, nasnet_utils.drop_path, slim.batch_norm],
      is_training=is_training):
    with arg_scope([slim.avg_pool2d, slim.max_pool2d, slim.conv2d,
                    slim.batch_norm, slim.separable_conv2d,
                    nasnet_utils.factorized_reduction,
                    nasnet_utils.global_avg_pool,
                    nasnet_utils.get_channel_index,
                    nasnet_utils.get_channel_dim],
                   data_format=hparams.data_format):
      return _build_pnasnet_base(
          images,
          normal_cell=normal_cell,
          num_classes=num_classes,
          hparams=hparams,
          is_training=is_training,
          final_endpoint=final_endpoint) 

# 需要导入模块: from nets.nasnet import nasnet_utils [as 别名]
# 或者: from nets.nasnet.nasnet_utils import factorized_reduction [as 别名]
def build_pnasnet_mobile(images,
                         num_classes,
                         is_training=True,
                         final_endpoint=None,
                         config=None):
  """Build PNASNet Mobile model for the ImageNet Dataset."""
  hparams = copy.deepcopy(config) if config else mobile_imagenet_config()
  # pylint: disable=protected-access
  nasnet._update_hparams(hparams, is_training)
  # pylint: enable=protected-access

  if tf.test.is_gpu_available() and hparams.data_format == 'NHWC':
    tf.logging.info('A GPU is available on the machine, consider using NCHW '
                    'data format for increased speed on GPU.')

  if hparams.data_format == 'NCHW':
    images = tf.transpose(images, [0, 3, 1, 2])

  # Calculate the total number of cells in the network.
  # There is no distinction between reduction and normal cells in PNAS so the
  # total number of cells is equal to the number normal cells plus the number
  # of stem cells (two by default).
  total_num_cells = hparams.num_cells + 2

  normal_cell = PNasNetNormalCell(hparams.num_conv_filters,
                                  hparams.drop_path_keep_prob, total_num_cells,
                                  hparams.total_training_steps)
  with arg_scope(
      [slim.dropout, nasnet_utils.drop_path, slim.batch_norm],
      is_training=is_training):
    with arg_scope(
        [
            slim.avg_pool2d, slim.max_pool2d, slim.conv2d, slim.batch_norm,
            slim.separable_conv2d, nasnet_utils.factorized_reduction,
            nasnet_utils.global_avg_pool, nasnet_utils.get_channel_index,
            nasnet_utils.get_channel_dim
        ],
        data_format=hparams.data_format):
      return _build_pnasnet_base(
          images,
          normal_cell=normal_cell,
          num_classes=num_classes,
          hparams=hparams,
          is_training=is_training,
          final_endpoint=final_endpoint) 

# 需要导入模块: from nets.nasnet import nasnet_utils [as 别名]
# 或者: from nets.nasnet.nasnet_utils import factorized_reduction [as 别名]
def build_nasnet_cifar(images, num_classes,
                       is_training=True,
                       config=None,
                       current_step=None):
  """Build NASNet model for the Cifar Dataset."""
  hparams = cifar_config() if config is None else copy.deepcopy(config)
  _update_hparams(hparams, is_training)

  if tf.test.is_gpu_available() and hparams.data_format == 'NHWC':
    tf.logging.info('A GPU is available on the machine, consider using NCHW '
                    'data format for increased speed on GPU.')

  if hparams.data_format == 'NCHW':
    images = tf.transpose(images, [0, 3, 1, 2])

  # Calculate the total number of cells in the network
  # Add 2 for the reduction cells
  total_num_cells = hparams.num_cells + 2

  normal_cell = nasnet_utils.NasNetANormalCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  reduction_cell = nasnet_utils.NasNetAReductionCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  with arg_scope([slim.dropout, nasnet_utils.drop_path, slim.batch_norm],
                 is_training=is_training):
    with arg_scope([slim.avg_pool2d,
                    slim.max_pool2d,
                    slim.conv2d,
                    slim.batch_norm,
                    slim.separable_conv2d,
                    nasnet_utils.factorized_reduction,
                    nasnet_utils.global_avg_pool,
                    nasnet_utils.get_channel_index,
                    nasnet_utils.get_channel_dim],
                   data_format=hparams.data_format):
      return _build_nasnet_base(images,
                                normal_cell=normal_cell,
                                reduction_cell=reduction_cell,
                                num_classes=num_classes,
                                hparams=hparams,
                                is_training=is_training,
                                stem_type='cifar',
                                current_step=current_step) 

# 需要导入模块: from nets.nasnet import nasnet_utils [as 别名]
# 或者: from nets.nasnet.nasnet_utils import factorized_reduction [as 别名]
def build_nasnet_mobile(images, num_classes,
                        is_training=True,
                        final_endpoint=None,
                        config=None,
                        current_step=None):
  """Build NASNet Mobile model for the ImageNet Dataset."""
  hparams = (mobile_imagenet_config() if config is None
             else copy.deepcopy(config))
  _update_hparams(hparams, is_training)

  if tf.test.is_gpu_available() and hparams.data_format == 'NHWC':
    tf.logging.info('A GPU is available on the machine, consider using NCHW '
                    'data format for increased speed on GPU.')

  if hparams.data_format == 'NCHW':
    images = tf.transpose(images, [0, 3, 1, 2])

  # Calculate the total number of cells in the network
  # Add 2 for the reduction cells
  total_num_cells = hparams.num_cells + 2
  # If ImageNet, then add an additional two for the stem cells
  total_num_cells += 2

  normal_cell = nasnet_utils.NasNetANormalCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  reduction_cell = nasnet_utils.NasNetAReductionCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  with arg_scope([slim.dropout, nasnet_utils.drop_path, slim.batch_norm],
                 is_training=is_training):
    with arg_scope([slim.avg_pool2d,
                    slim.max_pool2d,
                    slim.conv2d,
                    slim.batch_norm,
                    slim.separable_conv2d,
                    nasnet_utils.factorized_reduction,
                    nasnet_utils.global_avg_pool,
                    nasnet_utils.get_channel_index,
                    nasnet_utils.get_channel_dim],
                   data_format=hparams.data_format):
      return _build_nasnet_base(images,
                                normal_cell=normal_cell,
                                reduction_cell=reduction_cell,
                                num_classes=num_classes,
                                hparams=hparams,
                                is_training=is_training,
                                stem_type='imagenet',
                                final_endpoint=final_endpoint,
                                current_step=current_step) 

# 需要导入模块: from nets.nasnet import nasnet_utils [as 别名]
# 或者: from nets.nasnet.nasnet_utils import factorized_reduction [as 别名]
def build_nasnet_large(images, num_classes,
                       is_training=True,
                       final_endpoint=None,
                       config=None,
                       current_step=None):
  """Build NASNet Large model for the ImageNet Dataset."""
  hparams = (large_imagenet_config() if config is None
             else copy.deepcopy(config))
  _update_hparams(hparams, is_training)

  if tf.test.is_gpu_available() and hparams.data_format == 'NHWC':
    tf.logging.info('A GPU is available on the machine, consider using NCHW '
                    'data format for increased speed on GPU.')

  if hparams.data_format == 'NCHW':
    images = tf.transpose(images, [0, 3, 1, 2])

  # Calculate the total number of cells in the network
  # Add 2 for the reduction cells
  total_num_cells = hparams.num_cells + 2
  # If ImageNet, then add an additional two for the stem cells
  total_num_cells += 2

  normal_cell = nasnet_utils.NasNetANormalCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  reduction_cell = nasnet_utils.NasNetAReductionCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  with arg_scope([slim.dropout, nasnet_utils.drop_path, slim.batch_norm],
                 is_training=is_training):
    with arg_scope([slim.avg_pool2d,
                    slim.max_pool2d,
                    slim.conv2d,
                    slim.batch_norm,
                    slim.separable_conv2d,
                    nasnet_utils.factorized_reduction,
                    nasnet_utils.global_avg_pool,
                    nasnet_utils.get_channel_index,
                    nasnet_utils.get_channel_dim],
                   data_format=hparams.data_format):
      return _build_nasnet_base(images,
                                normal_cell=normal_cell,
                                reduction_cell=reduction_cell,
                                num_classes=num_classes,
                                hparams=hparams,
                                is_training=is_training,
                                stem_type='imagenet',
                                final_endpoint=final_endpoint,
                                current_step=current_step) 

# 需要导入模块: from nets.nasnet import nasnet_utils [as 别名]
# 或者: from nets.nasnet.nasnet_utils import factorized_reduction [as 别名]
def build_nasnet_mobile(images, num_classes,
                        is_training=True,
                        final_endpoint=None):
  """Build NASNet Mobile model for the ImageNet Dataset."""
  hparams = _mobile_imagenet_config()

  if tf.test.is_gpu_available() and hparams.data_format == 'NHWC':
    tf.logging.info('A GPU is available on the machine, consider using NCHW '
                    'data format for increased speed on GPU.')

  if hparams.data_format == 'NCHW':
    images = tf.transpose(images, [0, 3, 1, 2])

  # Calculate the total number of cells in the network
  # Add 2 for the reduction cells
  total_num_cells = hparams.num_cells + 2
  # If ImageNet, then add an additional two for the stem cells
  total_num_cells += 2

  normal_cell = nasnet_utils.NasNetANormalCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  reduction_cell = nasnet_utils.NasNetAReductionCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  with arg_scope([slim.dropout, nasnet_utils.drop_path, slim.batch_norm],
                 is_training=is_training):
    with arg_scope([slim.avg_pool2d,
                    slim.max_pool2d,
                    slim.conv2d,
                    slim.batch_norm,
                    slim.separable_conv2d,
                    nasnet_utils.factorized_reduction,
                    nasnet_utils.global_avg_pool,
                    nasnet_utils.get_channel_index,
                    nasnet_utils.get_channel_dim],
                   data_format=hparams.data_format):
      return _build_nasnet_base(images,
                                normal_cell=normal_cell,
                                reduction_cell=reduction_cell,
                                num_classes=num_classes,
                                hparams=hparams,
                                is_training=is_training,
                                stem_type='imagenet',
                                final_endpoint=final_endpoint) 

# 需要导入模块: from nets.nasnet import nasnet_utils [as 别名]
# 或者: from nets.nasnet.nasnet_utils import factorized_reduction [as 别名]
def build_nasnet_large(images, num_classes,
                       is_training=True,
                       final_endpoint=None):
  """Build NASNet Large model for the ImageNet Dataset."""
  hparams = _large_imagenet_config(is_training=is_training)

  if tf.test.is_gpu_available() and hparams.data_format == 'NHWC':
    tf.logging.info('A GPU is available on the machine, consider using NCHW '
                    'data format for increased speed on GPU.')

  if hparams.data_format == 'NCHW':
    images = tf.transpose(images, [0, 3, 1, 2])

  # Calculate the total number of cells in the network
  # Add 2 for the reduction cells
  total_num_cells = hparams.num_cells + 2
  # If ImageNet, then add an additional two for the stem cells
  total_num_cells += 2

  normal_cell = nasnet_utils.NasNetANormalCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  reduction_cell = nasnet_utils.NasNetAReductionCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  with arg_scope([slim.dropout, nasnet_utils.drop_path, slim.batch_norm],
                 is_training=is_training):
    with arg_scope([slim.avg_pool2d,
                    slim.max_pool2d,
                    slim.conv2d,
                    slim.batch_norm,
                    slim.separable_conv2d,
                    nasnet_utils.factorized_reduction,
                    nasnet_utils.global_avg_pool,
                    nasnet_utils.get_channel_index,
                    nasnet_utils.get_channel_dim],
                   data_format=hparams.data_format):
      return _build_nasnet_base(images,
                                normal_cell=normal_cell,
                                reduction_cell=reduction_cell,
                                num_classes=num_classes,
                                hparams=hparams,
                                is_training=is_training,
                                stem_type='imagenet',
                                final_endpoint=final_endpoint) 

# 需要导入模块: from nets.nasnet import nasnet_utils [as 别名]
# 或者: from nets.nasnet.nasnet_utils import factorized_reduction [as 别名]
def build_nasnet_cifar(images, num_classes,
                       is_training=True,
                       config=None):
  """Build NASNet model for the Cifar Dataset."""
  hparams = cifar_config() if config is None else copy.deepcopy(config)
  _update_hparams(hparams, is_training)

  if tf.test.is_gpu_available() and hparams.data_format == 'NHWC':
    tf.logging.info('A GPU is available on the machine, consider using NCHW '
                    'data format for increased speed on GPU.')

  if hparams.data_format == 'NCHW':
    images = tf.transpose(images, [0, 3, 1, 2])

  # Calculate the total number of cells in the network
  # Add 2 for the reduction cells
  total_num_cells = hparams.num_cells + 2

  normal_cell = nasnet_utils.NasNetANormalCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  reduction_cell = nasnet_utils.NasNetAReductionCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  with arg_scope([slim.dropout, nasnet_utils.drop_path, slim.batch_norm],
                 is_training=is_training):
    with arg_scope([slim.avg_pool2d,
                    slim.max_pool2d,
                    slim.conv2d,
                    slim.batch_norm,
                    slim.separable_conv2d,
                    nasnet_utils.factorized_reduction,
                    nasnet_utils.global_avg_pool,
                    nasnet_utils.get_channel_index,
                    nasnet_utils.get_channel_dim],
                   data_format=hparams.data_format):
      return _build_nasnet_base(images,
                                normal_cell=normal_cell,
                                reduction_cell=reduction_cell,
                                num_classes=num_classes,
                                hparams=hparams,
                                is_training=is_training,
                                stem_type='cifar') 

# 需要导入模块: from nets.nasnet import nasnet_utils [as 别名]
# 或者: from nets.nasnet.nasnet_utils import factorized_reduction [as 别名]
def build_nasnet_mobile(images, num_classes,
                        is_training=True,
                        final_endpoint=None,
                        config=None):
  """Build NASNet Mobile model for the ImageNet Dataset."""
  hparams = (mobile_imagenet_config() if config is None
             else copy.deepcopy(config))
  _update_hparams(hparams, is_training)

  if tf.test.is_gpu_available() and hparams.data_format == 'NHWC':
    tf.logging.info('A GPU is available on the machine, consider using NCHW '
                    'data format for increased speed on GPU.')

  if hparams.data_format == 'NCHW':
    images = tf.transpose(images, [0, 3, 1, 2])

  # Calculate the total number of cells in the network
  # Add 2 for the reduction cells
  total_num_cells = hparams.num_cells + 2
  # If ImageNet, then add an additional two for the stem cells
  total_num_cells += 2

  normal_cell = nasnet_utils.NasNetANormalCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  reduction_cell = nasnet_utils.NasNetAReductionCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  with arg_scope([slim.dropout, nasnet_utils.drop_path, slim.batch_norm],
                 is_training=is_training):
    with arg_scope([slim.avg_pool2d,
                    slim.max_pool2d,
                    slim.conv2d,
                    slim.batch_norm,
                    slim.separable_conv2d,
                    nasnet_utils.factorized_reduction,
                    nasnet_utils.global_avg_pool,
                    nasnet_utils.get_channel_index,
                    nasnet_utils.get_channel_dim],
                   data_format=hparams.data_format):
      return _build_nasnet_base(images,
                                normal_cell=normal_cell,
                                reduction_cell=reduction_cell,
                                num_classes=num_classes,
                                hparams=hparams,
                                is_training=is_training,
                                stem_type='imagenet',
                                final_endpoint=final_endpoint) 

# 需要导入模块: from nets.nasnet import nasnet_utils [as 别名]
# 或者: from nets.nasnet.nasnet_utils import factorized_reduction [as 别名]
def build_nasnet_large(images, num_classes,
                       is_training=True,
                       final_endpoint=None,
                       config=None):
  """Build NASNet Large model for the ImageNet Dataset."""
  hparams = (large_imagenet_config() if config is None
             else copy.deepcopy(config))
  _update_hparams(hparams, is_training)

  if tf.test.is_gpu_available() and hparams.data_format == 'NHWC':
    tf.logging.info('A GPU is available on the machine, consider using NCHW '
                    'data format for increased speed on GPU.')

  if hparams.data_format == 'NCHW':
    images = tf.transpose(images, [0, 3, 1, 2])

  # Calculate the total number of cells in the network
  # Add 2 for the reduction cells
  total_num_cells = hparams.num_cells + 2
  # If ImageNet, then add an additional two for the stem cells
  total_num_cells += 2

  normal_cell = nasnet_utils.NasNetANormalCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  reduction_cell = nasnet_utils.NasNetAReductionCell(
      hparams.num_conv_filters, hparams.drop_path_keep_prob,
      total_num_cells, hparams.total_training_steps)
  with arg_scope([slim.dropout, nasnet_utils.drop_path, slim.batch_norm],
                 is_training=is_training):
    with arg_scope([slim.avg_pool2d,
                    slim.max_pool2d,
                    slim.conv2d,
                    slim.batch_norm,
                    slim.separable_conv2d,
                    nasnet_utils.factorized_reduction,
                    nasnet_utils.global_avg_pool,
                    nasnet_utils.get_channel_index,
                    nasnet_utils.get_channel_dim],
                   data_format=hparams.data_format):
      return _build_nasnet_base(images,
                                normal_cell=normal_cell,
                                reduction_cell=reduction_cell,
                                num_classes=num_classes,
                                hparams=hparams,
                                is_training=is_training,
                                stem_type='imagenet',
                                final_endpoint=final_endpoint)