Python nets.mobilenet_v1.mobilenet_v1_arg_scope() Examples
The following are 30
code examples of nets.mobilenet_v1.mobilenet_v1_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.mobilenet_v1
, or try the search function
.
.
Example #1
| Source File: mobilenet_v1_eval.py From MAX-Image-Segmenter with Apache License 2.0 | 5 votes |
|
def build_model():
"""Build the mobilenet_v1 model for evaluation.
Returns:
g: graph with rewrites after insertion of quantization ops and batch norm
folding.
eval_ops: eval ops for inference.
variables_to_restore: List of variables to restore from checkpoint.
"""
g = tf.Graph()
with g.as_default():
inputs, labels = imagenet_input(is_training=False)
scope = mobilenet_v1.mobilenet_v1_arg_scope(
is_training=False, weight_decay=0.0)
with slim.arg_scope(scope):
logits, _ = mobilenet_v1.mobilenet_v1(
inputs,
is_training=False,
depth_multiplier=FLAGS.depth_multiplier,
num_classes=FLAGS.num_classes)
if FLAGS.quantize:
tf.contrib.quantize.create_eval_graph()
eval_ops = metrics(logits, labels)
return g, eval_ops
Example #2
| Source File: mobilenet_v1_test.py From models with Apache License 2.0 | 5 votes |
|
def testBatchNormScopeDoesHasIsTrainingWhenItsNotNone(self):
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=True)
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=False)
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
sc = mobilenet_v1.mobilenet_v1_arg_scope()
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
Example #3
| Source File: faster_rcnn_mobilenet_v1_feature_extractor.py From Person-Detection-and-Tracking with MIT License | 5 votes |
|
def _extract_box_classifier_features(self, proposal_feature_maps, scope):
"""Extracts second stage box classifier features.
Args:
proposal_feature_maps: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, crop_height, crop_width, depth]
representing the feature map cropped to each proposal.
scope: A scope name (unused).
Returns:
proposal_classifier_features: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, height, width, depth]
representing box classifier features for each proposal.
"""
net = proposal_feature_maps
conv_depth = 1024
if self._skip_last_stride:
conv_depth_ratio = float(self._conv_depth_ratio_in_percentage) / 100.0
conv_depth = int(float(conv_depth) * conv_depth_ratio)
depth = lambda d: max(int(d * 1.0), 16)
with tf.variable_scope('MobilenetV1', reuse=self._reuse_weights):
with slim.arg_scope(
mobilenet_v1.mobilenet_v1_arg_scope(
is_training=self._train_batch_norm,
weight_decay=self._weight_decay)):
with slim.arg_scope(
[slim.conv2d, slim.separable_conv2d], padding='SAME'):
net = slim.separable_conv2d(
net,
depth(conv_depth), [3, 3],
depth_multiplier=1,
stride=2,
scope='Conv2d_12_pointwise')
return slim.separable_conv2d(
net,
depth(conv_depth), [3, 3],
depth_multiplier=1,
stride=1,
scope='Conv2d_13_pointwise')
Example #4
| Source File: faster_rcnn_mobilenet_v1_feature_extractor.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def _extract_box_classifier_features(self, proposal_feature_maps, scope):
"""Extracts second stage box classifier features.
Args:
proposal_feature_maps: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, crop_height, crop_width, depth]
representing the feature map cropped to each proposal.
scope: A scope name (unused).
Returns:
proposal_classifier_features: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, height, width, depth]
representing box classifier features for each proposal.
"""
net = proposal_feature_maps
conv_depth = 1024
if self._skip_last_stride:
conv_depth_ratio = float(self._conv_depth_ratio_in_percentage) / 100.0
conv_depth = int(float(conv_depth) * conv_depth_ratio)
depth = lambda d: max(int(d * 1.0), 16)
with tf.variable_scope('MobilenetV1', reuse=self._reuse_weights):
with slim.arg_scope(
mobilenet_v1.mobilenet_v1_arg_scope(
is_training=self._train_batch_norm,
weight_decay=self._weight_decay)):
with slim.arg_scope(
[slim.conv2d, slim.separable_conv2d], padding='SAME'):
net = slim.separable_conv2d(
net,
depth(conv_depth), [3, 3],
depth_multiplier=1,
stride=2,
scope='Conv2d_12_pointwise')
return slim.separable_conv2d(
net,
depth(conv_depth), [3, 3],
depth_multiplier=1,
stride=1,
scope='Conv2d_13_pointwise')
Example #5
| Source File: mobilenet_v1_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def testBatchNormScopeDoesHasIsTrainingWhenItsNotNone(self):
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=True)
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=False)
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
sc = mobilenet_v1.mobilenet_v1_arg_scope()
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
Example #6
| Source File: faster_rcnn_mobilenet_v1_feature_extractor.py From ros_tensorflow with Apache License 2.0 | 5 votes |
|
def _extract_box_classifier_features(self, proposal_feature_maps, scope):
"""Extracts second stage box classifier features.
Args:
proposal_feature_maps: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, crop_height, crop_width, depth]
representing the feature map cropped to each proposal.
scope: A scope name (unused).
Returns:
proposal_classifier_features: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, height, width, depth]
representing box classifier features for each proposal.
"""
net = proposal_feature_maps
conv_depth = 1024
if self._skip_last_stride:
conv_depth_ratio = float(self._conv_depth_ratio_in_percentage) / 100.0
conv_depth = int(float(conv_depth) * conv_depth_ratio)
depth = lambda d: max(int(d * 1.0), 16)
with tf.variable_scope('MobilenetV1', reuse=self._reuse_weights):
with slim.arg_scope(
mobilenet_v1.mobilenet_v1_arg_scope(
is_training=self._train_batch_norm,
weight_decay=self._weight_decay)):
with slim.arg_scope(
[slim.conv2d, slim.separable_conv2d], padding='SAME'):
net = slim.separable_conv2d(
net,
depth(conv_depth), [3, 3],
depth_multiplier=1,
stride=2,
scope='Conv2d_12_pointwise')
return slim.separable_conv2d(
net,
depth(conv_depth), [3, 3],
depth_multiplier=1,
stride=1,
scope='Conv2d_13_pointwise')
Example #7
| Source File: mobilenet_v1_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def testBatchNormScopeDoesNotHaveIsTrainingWhenItsSetToNone(self):
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=None)
self.assertNotIn('is_training', sc[slim.arg_scope_func_key(
slim.batch_norm)])
Example #8
| Source File: mobilenet_v1_eval.py From BMW-TensorFlow-Training-GUI with Apache License 2.0 | 5 votes |
|
def build_model():
"""Build the mobilenet_v1 model for evaluation.
Returns:
g: graph with rewrites after insertion of quantization ops and batch norm
folding.
eval_ops: eval ops for inference.
variables_to_restore: List of variables to restore from checkpoint.
"""
g = tf.Graph()
with g.as_default():
inputs, labels = imagenet_input(is_training=False)
scope = mobilenet_v1.mobilenet_v1_arg_scope(
is_training=False, weight_decay=0.0)
with slim.arg_scope(scope):
logits, _ = mobilenet_v1.mobilenet_v1(
inputs,
is_training=False,
depth_multiplier=FLAGS.depth_multiplier,
num_classes=FLAGS.num_classes)
if FLAGS.quantize:
tf.contrib.quantize.create_eval_graph()
eval_ops = metrics(logits, labels)
return g, eval_ops
Example #9
| Source File: mobilenet_v1_test.py From BMW-TensorFlow-Training-GUI with Apache License 2.0 | 5 votes |
|
def testBatchNormScopeDoesNotHaveIsTrainingWhenItsSetToNone(self):
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=None)
self.assertNotIn('is_training', sc[slim.arg_scope_func_key(
slim.batch_norm)])
Example #10
| Source File: mobilenet_v1_test.py From BMW-TensorFlow-Training-GUI with Apache License 2.0 | 5 votes |
|
def testBatchNormScopeDoesHasIsTrainingWhenItsNotNone(self):
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=True)
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=False)
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
sc = mobilenet_v1.mobilenet_v1_arg_scope()
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
Example #11
| Source File: ssd_mobilenet_v1_ppn_feature_extractor.py From BMW-TensorFlow-Training-GUI with Apache License 2.0 | 5 votes |
|
def extract_features(self, preprocessed_inputs):
"""Extract features from preprocessed inputs.
Args:
preprocessed_inputs: a [batch, height, width, channels] float tensor
representing a batch of images.
Returns:
feature_maps: a list of tensors where the ith tensor has shape
[batch, height_i, width_i, depth_i]
"""
preprocessed_inputs = shape_utils.check_min_image_dim(
33, preprocessed_inputs)
with tf.variable_scope('MobilenetV1',
reuse=self._reuse_weights) as scope:
with slim.arg_scope(
mobilenet_v1.mobilenet_v1_arg_scope(
is_training=None, regularize_depthwise=True)):
with (slim.arg_scope(self._conv_hyperparams_fn())
if self._override_base_feature_extractor_hyperparams
else context_manager.IdentityContextManager()):
_, image_features = mobilenet_v1.mobilenet_v1_base(
ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
final_endpoint='Conv2d_13_pointwise',
min_depth=self._min_depth,
depth_multiplier=self._depth_multiplier,
use_explicit_padding=self._use_explicit_padding,
scope=scope)
with slim.arg_scope(self._conv_hyperparams_fn()):
feature_maps = feature_map_generators.pooling_pyramid_feature_maps(
base_feature_map_depth=0,
num_layers=6,
image_features={
'image_features': image_features['Conv2d_11_pointwise']
})
return feature_maps.values()
Example #12
| Source File: faster_rcnn_mobilenet_v1_feature_extractor.py From BMW-TensorFlow-Training-GUI with Apache License 2.0 | 5 votes |
|
def _extract_box_classifier_features(self, proposal_feature_maps, scope):
"""Extracts second stage box classifier features.
Args:
proposal_feature_maps: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, crop_height, crop_width, depth]
representing the feature map cropped to each proposal.
scope: A scope name (unused).
Returns:
proposal_classifier_features: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, height, width, depth]
representing box classifier features for each proposal.
"""
net = proposal_feature_maps
conv_depth = 1024
if self._skip_last_stride:
conv_depth_ratio = float(self._conv_depth_ratio_in_percentage) / 100.0
conv_depth = int(float(conv_depth) * conv_depth_ratio)
depth = lambda d: max(int(d * 1.0), 16)
with tf.variable_scope('MobilenetV1', reuse=self._reuse_weights):
with slim.arg_scope(
mobilenet_v1.mobilenet_v1_arg_scope(
is_training=self._train_batch_norm,
weight_decay=self._weight_decay)):
with slim.arg_scope(
[slim.conv2d, slim.separable_conv2d], padding='SAME'):
net = slim.separable_conv2d(
net,
depth(conv_depth), [3, 3],
depth_multiplier=1,
stride=2,
scope='Conv2d_12_pointwise')
return slim.separable_conv2d(
net,
depth(conv_depth), [3, 3],
depth_multiplier=1,
stride=1,
scope='Conv2d_13_pointwise')
Example #13
| Source File: mobilenet_v1_eval.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def build_model():
"""Build the mobilenet_v1 model for evaluation.
Returns:
g: graph with rewrites after insertion of quantization ops and batch norm
folding.
eval_ops: eval ops for inference.
variables_to_restore: List of variables to restore from checkpoint.
"""
g = tf.Graph()
with g.as_default():
inputs, labels = imagenet_input(is_training=False)
scope = mobilenet_v1.mobilenet_v1_arg_scope(
is_training=False, weight_decay=0.0)
with slim.arg_scope(scope):
logits, _ = mobilenet_v1.mobilenet_v1(
inputs,
is_training=False,
depth_multiplier=FLAGS.depth_multiplier,
num_classes=FLAGS.num_classes)
if FLAGS.quantize:
tf.contrib.quantize.create_eval_graph()
eval_ops = metrics(logits, labels)
return g, eval_ops
Example #14
| Source File: mobilenet_v1_eval.py From DeepLab_v3 with MIT License | 5 votes |
|
def build_model():
"""Build the mobilenet_v1 model for evaluation.
Returns:
g: graph with rewrites after insertion of quantization ops and batch norm
folding.
eval_ops: eval ops for inference.
variables_to_restore: List of variables to restore from checkpoint.
"""
g = tf.Graph()
with g.as_default():
inputs, labels = imagenet_input(is_training=False)
scope = mobilenet_v1.mobilenet_v1_arg_scope(
is_training=False, weight_decay=0.0)
with slim.arg_scope(scope):
logits, _ = mobilenet_v1.mobilenet_v1(
inputs,
is_training=False,
depth_multiplier=FLAGS.depth_multiplier,
num_classes=FLAGS.num_classes)
if FLAGS.quantize:
tf.contrib.quantize.create_eval_graph()
eval_ops = metrics(logits, labels)
return g, eval_ops
Example #15
| Source File: mobilenet_v1_eval.py From ICPR_TextDection with GNU General Public License v3.0 | 5 votes |
|
def build_model():
"""Build the mobilenet_v1 model for evaluation.
Returns:
g: graph with rewrites after insertion of quantization ops and batch norm
folding.
eval_ops: eval ops for inference.
variables_to_restore: List of variables to restore from checkpoint.
"""
g = tf.Graph()
with g.as_default():
inputs, labels = imagenet_input(is_training=False)
scope = mobilenet_v1.mobilenet_v1_arg_scope(
is_training=False, weight_decay=0.0)
with slim.arg_scope(scope):
logits, _ = mobilenet_v1.mobilenet_v1(
inputs,
is_training=False,
depth_multiplier=FLAGS.depth_multiplier,
num_classes=FLAGS.num_classes)
if FLAGS.quantize:
tf.contrib.quantize.create_eval_graph()
eval_ops = metrics(logits, labels)
return g, eval_ops
Example #16
| Source File: ssd_mobilenet_v1_ppn_feature_extractor.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def extract_features(self, preprocessed_inputs):
"""Extract features from preprocessed inputs.
Args:
preprocessed_inputs: a [batch, height, width, channels] float tensor
representing a batch of images.
Returns:
feature_maps: a list of tensors where the ith tensor has shape
[batch, height_i, width_i, depth_i]
"""
preprocessed_inputs = shape_utils.check_min_image_dim(
33, preprocessed_inputs)
with tf.variable_scope('MobilenetV1',
reuse=self._reuse_weights) as scope:
with slim.arg_scope(
mobilenet_v1.mobilenet_v1_arg_scope(
is_training=None, regularize_depthwise=True)):
with (slim.arg_scope(self._conv_hyperparams_fn())
if self._override_base_feature_extractor_hyperparams
else context_manager.IdentityContextManager()):
_, image_features = mobilenet_v1.mobilenet_v1_base(
ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
final_endpoint='Conv2d_13_pointwise',
min_depth=self._min_depth,
depth_multiplier=self._depth_multiplier,
use_explicit_padding=self._use_explicit_padding,
scope=scope)
with slim.arg_scope(self._conv_hyperparams_fn()):
feature_maps = feature_map_generators.pooling_pyramid_feature_maps(
base_feature_map_depth=0,
num_layers=6,
image_features={
'image_features': image_features['Conv2d_11_pointwise']
})
return feature_maps.values()
Example #17
| Source File: faster_rcnn_mobilenet_v1_feature_extractor.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def _extract_box_classifier_features(self, proposal_feature_maps, scope):
"""Extracts second stage box classifier features.
Args:
proposal_feature_maps: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, crop_height, crop_width, depth]
representing the feature map cropped to each proposal.
scope: A scope name (unused).
Returns:
proposal_classifier_features: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, height, width, depth]
representing box classifier features for each proposal.
"""
net = proposal_feature_maps
conv_depth = 1024
if self._skip_last_stride:
conv_depth_ratio = float(self._conv_depth_ratio_in_percentage) / 100.0
conv_depth = int(float(conv_depth) * conv_depth_ratio)
depth = lambda d: max(int(d * 1.0), 16)
with tf.variable_scope('MobilenetV1', reuse=self._reuse_weights):
with slim.arg_scope(
mobilenet_v1.mobilenet_v1_arg_scope(
is_training=self._train_batch_norm,
weight_decay=self._weight_decay)):
with slim.arg_scope(
[slim.conv2d, slim.separable_conv2d], padding='SAME'):
net = slim.separable_conv2d(
net,
depth(conv_depth), [3, 3],
depth_multiplier=1,
stride=2,
scope='Conv2d_12_pointwise')
return slim.separable_conv2d(
net,
depth(conv_depth), [3, 3],
depth_multiplier=1,
stride=1,
scope='Conv2d_13_pointwise')
Example #18
| Source File: mobilenet_v1_test.py From MAX-Image-Segmenter with Apache License 2.0 | 5 votes |
|
def testBatchNormScopeDoesNotHaveIsTrainingWhenItsSetToNone(self):
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=None)
self.assertNotIn('is_training', sc[slim.arg_scope_func_key(
slim.batch_norm)])
Example #19
| Source File: mobilenet_v1_test.py From MAX-Image-Segmenter with Apache License 2.0 | 5 votes |
|
def testBatchNormScopeDoesHasIsTrainingWhenItsNotNone(self):
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=True)
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=False)
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
sc = mobilenet_v1.mobilenet_v1_arg_scope()
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
Example #20
| Source File: train_PoseTrack_COCO_17_mobile_deconv.py From lighttrack with MIT License | 5 votes |
|
def head_net(self, blocks, is_training, trainable=True):
normal_initializer = tf.truncated_normal_initializer(0, 0.01)
msra_initializer = tf.contrib.layers.variance_scaling_initializer()
xavier_initializer = tf.contrib.layers.xavier_initializer()
with slim.arg_scope(mobilenet_v1_arg_scope(is_training=is_training)):
out = slim.conv2d_transpose(blocks, 256, [4, 4], stride=2,
trainable=trainable, weights_initializer=normal_initializer,
padding='SAME', activation_fn=tf.nn.relu,
scope='up1')
out = slim.conv2d_transpose(out, 256, [4, 4], stride=2,
trainable=trainable, weights_initializer=normal_initializer,
padding='SAME', activation_fn=tf.nn.relu,
scope='up2')
out = slim.conv2d_transpose(out, 256, [4, 4], stride=2,
trainable=trainable, weights_initializer=normal_initializer,
padding='SAME', activation_fn=tf.nn.relu,
scope='up3')
out = slim.conv2d(out, cfg.nr_skeleton, [1, 1],
trainable=trainable, weights_initializer=msra_initializer,
padding='SAME', normalizer_fn=None, activation_fn=None,
scope='out')
return out
Example #21
| Source File: network_mobile_deconv.py From lighttrack with MIT License | 5 votes |
|
def head_net(self, blocks, is_training, trainable=True):
normal_initializer = tf.truncated_normal_initializer(0, 0.01)
msra_initializer = tf.contrib.layers.variance_scaling_initializer()
xavier_initializer = tf.contrib.layers.xavier_initializer()
with slim.arg_scope(mobilenet_v1_arg_scope(is_training=is_training)):
out = slim.conv2d_transpose(blocks, 256, [4, 4], stride=2,
trainable=trainable, weights_initializer=normal_initializer,
padding='SAME', activation_fn=tf.nn.relu,
scope='up1')
out = slim.conv2d_transpose(out, 256, [4, 4], stride=2,
trainable=trainable, weights_initializer=normal_initializer,
padding='SAME', activation_fn=tf.nn.relu,
scope='up2')
out = slim.conv2d_transpose(out, 256, [4, 4], stride=2,
trainable=trainable, weights_initializer=normal_initializer,
padding='SAME', activation_fn=tf.nn.relu,
scope='up3')
out = slim.conv2d(out, cfg.nr_skeleton, [1, 1],
trainable=trainable, weights_initializer=msra_initializer,
padding='SAME', normalizer_fn=None, activation_fn=None,
scope='out')
return out
Example #22
| Source File: ssd_mobilenet_v1_ppn_feature_extractor.py From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 | 5 votes |
|
def extract_features(self, preprocessed_inputs):
"""Extract features from preprocessed inputs.
Args:
preprocessed_inputs: a [batch, height, width, channels] float tensor
representing a batch of images.
Returns:
feature_maps: a list of tensors where the ith tensor has shape
[batch, height_i, width_i, depth_i]
"""
preprocessed_inputs = shape_utils.check_min_image_dim(
33, preprocessed_inputs)
with tf.variable_scope('MobilenetV1',
reuse=self._reuse_weights) as scope:
with slim.arg_scope(
mobilenet_v1.mobilenet_v1_arg_scope(
is_training=None, regularize_depthwise=True)):
with (slim.arg_scope(self._conv_hyperparams_fn())
if self._override_base_feature_extractor_hyperparams
else context_manager.IdentityContextManager()):
_, image_features = mobilenet_v1.mobilenet_v1_base(
ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
final_endpoint='Conv2d_13_pointwise',
min_depth=self._min_depth,
depth_multiplier=self._depth_multiplier,
use_explicit_padding=self._use_explicit_padding,
scope=scope)
with slim.arg_scope(self._conv_hyperparams_fn()):
feature_maps = feature_map_generators.pooling_pyramid_feature_maps(
base_feature_map_depth=0,
num_layers=6,
image_features={
'image_features': image_features['Conv2d_11_pointwise']
})
return feature_maps.values()
Example #23
| Source File: ssd_mobilenet_v1_ppn_feature_extractor.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def extract_features(self, preprocessed_inputs):
"""Extract features from preprocessed inputs.
Args:
preprocessed_inputs: a [batch, height, width, channels] float tensor
representing a batch of images.
Returns:
feature_maps: a list of tensors where the ith tensor has shape
[batch, height_i, width_i, depth_i]
"""
preprocessed_inputs = shape_utils.check_min_image_dim(
33, preprocessed_inputs)
with tf.variable_scope('MobilenetV1',
reuse=self._reuse_weights) as scope:
with slim.arg_scope(
mobilenet_v1.mobilenet_v1_arg_scope(
is_training=None, regularize_depthwise=True)):
with (slim.arg_scope(self._conv_hyperparams_fn())
if self._override_base_feature_extractor_hyperparams
else context_manager.IdentityContextManager()):
_, image_features = mobilenet_v1.mobilenet_v1_base(
ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
final_endpoint='Conv2d_13_pointwise',
min_depth=self._min_depth,
depth_multiplier=self._depth_multiplier,
use_explicit_padding=self._use_explicit_padding,
scope=scope)
with slim.arg_scope(self._conv_hyperparams_fn()):
feature_maps = feature_map_generators.pooling_pyramid_feature_maps(
base_feature_map_depth=0,
num_layers=6,
image_features={
'image_features': image_features['Conv2d_11_pointwise']
})
return feature_maps.values()
Example #24
| Source File: faster_rcnn_mobilenet_v1_feature_extractor.py From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 | 5 votes |
|
def _extract_box_classifier_features(self, proposal_feature_maps, scope):
"""Extracts second stage box classifier features.
Args:
proposal_feature_maps: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, crop_height, crop_width, depth]
representing the feature map cropped to each proposal.
scope: A scope name (unused).
Returns:
proposal_classifier_features: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, height, width, depth]
representing box classifier features for each proposal.
"""
net = proposal_feature_maps
conv_depth = 1024
if self._skip_last_stride:
conv_depth_ratio = float(self._conv_depth_ratio_in_percentage) / 100.0
conv_depth = int(float(conv_depth) * conv_depth_ratio)
depth = lambda d: max(int(d * 1.0), 16)
with tf.variable_scope('MobilenetV1', reuse=self._reuse_weights):
with slim.arg_scope(
mobilenet_v1.mobilenet_v1_arg_scope(
is_training=self._train_batch_norm,
weight_decay=self._weight_decay)):
with slim.arg_scope(
[slim.conv2d, slim.separable_conv2d], padding='SAME'):
net = slim.separable_conv2d(
net,
depth(conv_depth), [3, 3],
depth_multiplier=1,
stride=2,
scope='Conv2d_12_pointwise')
return slim.separable_conv2d(
net,
depth(conv_depth), [3, 3],
depth_multiplier=1,
stride=1,
scope='Conv2d_13_pointwise')
Example #25
| Source File: mobilenet_v1_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def testBatchNormScopeDoesHasIsTrainingWhenItsNotNone(self):
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=True)
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=False)
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
sc = mobilenet_v1.mobilenet_v1_arg_scope()
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
Example #26
| Source File: mobilenet_v1_eval.py From SENet-tensorflow-slim with MIT License | 5 votes |
|
def build_model():
"""Build the mobilenet_v1 model for evaluation.
Returns:
g: graph with rewrites after insertion of quantization ops and batch norm
folding.
eval_ops: eval ops for inference.
variables_to_restore: List of variables to restore from checkpoint.
"""
g = tf.Graph()
with g.as_default():
inputs, labels = imagenet_input(is_training=False)
scope = mobilenet_v1.mobilenet_v1_arg_scope(
is_training=False, weight_decay=0.0)
with slim.arg_scope(scope):
logits, _ = mobilenet_v1.mobilenet_v1(
inputs,
is_training=False,
depth_multiplier=FLAGS.depth_multiplier,
num_classes=FLAGS.num_classes)
if FLAGS.quantize:
tf.contrib.quantize.create_eval_graph()
eval_ops = metrics(logits, labels)
return g, eval_ops
Example #27
| Source File: mobilenet_v1_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def testBatchNormScopeDoesNotHaveIsTrainingWhenItsSetToNone(self):
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=None)
self.assertNotIn('is_training', sc[slim.arg_scope_func_key(
slim.batch_norm)])
Example #28
| Source File: mobilenet_v1_test.py From SENet-tensorflow-slim with MIT License | 5 votes |
|
def testBatchNormScopeDoesNotHaveIsTrainingWhenItsSetToNone(self):
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=None)
self.assertNotIn('is_training', sc[slim.arg_scope_func_key(
slim.batch_norm)])
Example #29
| Source File: mobilenet_v1_test.py From SENet-tensorflow-slim with MIT License | 5 votes |
|
def testBatchNormScopeDoesHasIsTrainingWhenItsNotNone(self):
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=True)
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=False)
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
sc = mobilenet_v1.mobilenet_v1_arg_scope()
self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
Example #30
| Source File: mobilenet_v1_eval.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def build_model():
"""Build the mobilenet_v1 model for evaluation.
Returns:
g: graph with rewrites after insertion of quantization ops and batch norm
folding.
eval_ops: eval ops for inference.
variables_to_restore: List of variables to restore from checkpoint.
"""
g = tf.Graph()
with g.as_default():
inputs, labels = imagenet_input(is_training=False)
scope = mobilenet_v1.mobilenet_v1_arg_scope(
is_training=False, weight_decay=0.0)
with slim.arg_scope(scope):
logits, _ = mobilenet_v1.mobilenet_v1(
inputs,
is_training=False,
depth_multiplier=FLAGS.depth_multiplier,
num_classes=FLAGS.num_classes)
if FLAGS.quantize:
tf.contrib.quantize.create_eval_graph()
eval_ops = metrics(logits, labels)
return g, eval_ops
