Python源码示例：nets.nasnet.nasnet._update_hparams()
示例1
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)
示例2
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)
示例3
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)
示例4
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)
示例5
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)
示例6
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)
示例7
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)
示例8
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)
示例9
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)
示例10
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,
hparams.use_bounded_activation)
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)
示例11
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,
hparams.use_bounded_activation)
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)
示例12
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)
示例13
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,
hparams.use_bounded_activation)
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)
示例14
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,
hparams.use_bounded_activation)
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)
示例15
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,
hparams.use_bounded_activation)
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)
示例16
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,
hparams.use_bounded_activation)
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)
示例17
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(a=images, perm=[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,
hparams.use_bounded_activation)
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)
示例18
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(a=images, perm=[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,
hparams.use_bounded_activation)
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)
示例19
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)
示例20
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)
