Python nets.nasnet.nasnet._update_hparams() Examples
The following are 20
code examples of nets.nasnet.nasnet._update_hparams().
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: pnasnet.py From MAX-Image-Segmenter with Apache License 2.0 | 4 votes |
|
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)
Example #2
| Source File: pnasnet.py From multilabel-image-classification-tensorflow with MIT License | 4 votes |
|
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)
Example #3
| Source File: pnasnet.py From multilabel-image-classification-tensorflow with MIT License | 4 votes |
|
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)
Example #4
| Source File: pnasnet.py From models with Apache License 2.0 | 4 votes |
|
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)
Example #5
| Source File: pnasnet.py From models with Apache License 2.0 | 4 votes |
|
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)
Example #6
| Source File: pnasnet.py From g-tensorflow-models with Apache License 2.0 | 4 votes |
|
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)
Example #7
| Source File: pnasnet.py From g-tensorflow-models with Apache License 2.0 | 4 votes |
|
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)
Example #8
| Source File: pnasnet.py From MAX-Object-Detector with Apache License 2.0 | 4 votes |
|
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)
Example #9
| Source File: pnasnet.py From MAX-Object-Detector with Apache License 2.0 | 4 votes |
|
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)
Example #10
| Source File: pnasnet.py From SENet-tensorflow-slim with MIT License | 4 votes |
|
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)
Example #11
| Source File: pnasnet.py From DeepLab_v3 with MIT License | 4 votes |
|
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)
Example #12
| Source File: pnasnet.py From MAX-Image-Segmenter with Apache License 2.0 | 4 votes |
|
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)
Example #13
| Source File: pnasnet.py From BMW-TensorFlow-Training-GUI with Apache License 2.0 | 4 votes |
|
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)
Example #14
| Source File: pnasnet.py From BMW-TensorFlow-Training-GUI with Apache License 2.0 | 4 votes |
|
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)
Example #15
| Source File: pnasnet.py From Gun-Detector with Apache License 2.0 | 4 votes |
|
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)
Example #16
| Source File: pnasnet.py From CBAM-tensorflow-slim with MIT License | 4 votes |
|
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)
Example #17
| Source File: pnasnet.py From edafa with MIT License | 4 votes |
|
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)
Example #18
| Source File: pnasnet.py From edafa with MIT License | 4 votes |
|
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)
Example #19
| Source File: pnasnet.py From CVTron with Apache License 2.0 | 4 votes |
|
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)
Example #20
| Source File: pnasnet.py From DeepLab_v3 with MIT License | 4 votes |
|
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)
