Python tensorflow.op_scope() Examples
The following are 30
code examples of tensorflow.op_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
tensorflow
, or try the search function
.
.
Example #1
| Source File: image_processing.py From terngrad with Apache License 2.0 | 6 votes |
|
def eval_cifar10_image(image, height, width, scope=None):
"""Prepare one image for evaluation.
Args:
image: 3-D float Tensor
height: integer
width: integer
scope: Optional scope for op_scope.
Returns:
3-D float Tensor of prepared image.
"""
with tf.name_scope(scope, 'eval_image', [image, height, width]):
# Image processing for evaluation.
# Crop the central [height, width] of the image.
image = tf.image.resize_image_with_crop_or_pad(image, height, width)
# Subtract off the mean and divide by the variance of the pixels.
image = tf.image.per_image_standardization(image)
image.set_shape([height, width, 3])
return image
Example #2
| Source File: losses.py From inception_v3 with Apache License 2.0 | 6 votes |
|
def l1_l2_regularizer(weight_l1=1.0, weight_l2=1.0, scope=None):
"""Define a L1L2 regularizer.
Args:
weight_l1: scale the L1 loss by this factor.
weight_l2: scale the L2 loss by this factor.
scope: Optional scope for op_scope.
Returns:
a regularizer function.
"""
def regularizer(tensor):
with tf.op_scope([tensor], scope, 'L1L2Regularizer'):
weight_l1_t = tf.convert_to_tensor(weight_l1,
dtype=tensor.dtype.base_dtype,
name='weight_l1')
weight_l2_t = tf.convert_to_tensor(weight_l2,
dtype=tensor.dtype.base_dtype,
name='weight_l2')
reg_l1 = tf.mul(weight_l1_t, tf.reduce_sum(tf.abs(tensor)),
name='value_l1')
reg_l2 = tf.mul(weight_l2_t, tf.nn.l2_loss(tensor),
name='value_l2')
return tf.add(reg_l1, reg_l2, name='value')
return regularizer
Example #3
| Source File: preprocessing.py From parallax with Apache License 2.0 | 6 votes |
|
def decode_jpeg(image_buffer, scope=None): # , dtype=tf.float32):
"""Decode a JPEG string into one 3-D float image Tensor.
Args:
image_buffer: scalar string Tensor.
scope: Optional scope for op_scope.
Returns:
3-D float Tensor with values ranging from [0, 1).
"""
# with tf.op_scope([image_buffer], scope, 'decode_jpeg'):
# with tf.name_scope(scope, 'decode_jpeg', [image_buffer]):
with tf.name_scope(scope or 'decode_jpeg'):
# Decode the string as an RGB JPEG.
# Note that the resulting image contains an unknown height and width
# that is set dynamically by decode_jpeg. In other words, the height
# and width of image is unknown at compile-time.
image = tf.image.decode_jpeg(image_buffer, channels=3,
fancy_upscaling=False,
dct_method='INTEGER_FAST')
# image = tf.Print(image, [tf.shape(image)], 'Image shape: ')
return image
Example #4
| Source File: losses.py From deeplearning-benchmark with Apache License 2.0 | 6 votes |
|
def l1_regularizer(weight=1.0, scope=None):
"""Define a L1 regularizer.
Args:
weight: scale the loss by this factor.
scope: Optional scope for op_scope.
Returns:
a regularizer function.
"""
def regularizer(tensor):
with tf.op_scope([tensor], scope, 'L1Regularizer'):
l1_weight = tf.convert_to_tensor(weight,
dtype=tensor.dtype.base_dtype,
name='weight')
return tf.mul(l1_weight, tf.reduce_sum(tf.abs(tensor)), name='value')
return regularizer
Example #5
| Source File: losses.py From deeplearning-benchmark with Apache License 2.0 | 6 votes |
|
def l2_regularizer(weight=1.0, scope=None):
"""Define a L2 regularizer.
Args:
weight: scale the loss by this factor.
scope: Optional scope for op_scope.
Returns:
a regularizer function.
"""
def regularizer(tensor):
with tf.op_scope([tensor], scope, 'L2Regularizer'):
l2_weight = tf.convert_to_tensor(weight,
dtype=tensor.dtype.base_dtype,
name='weight')
return tf.mul(l2_weight, tf.nn.l2_loss(tensor), name='value')
return regularizer
Example #6
| Source File: losses.py From deeplearning-benchmark with Apache License 2.0 | 6 votes |
|
def l1_l2_regularizer(weight_l1=1.0, weight_l2=1.0, scope=None):
"""Define a L1L2 regularizer.
Args:
weight_l1: scale the L1 loss by this factor.
weight_l2: scale the L2 loss by this factor.
scope: Optional scope for op_scope.
Returns:
a regularizer function.
"""
def regularizer(tensor):
with tf.op_scope([tensor], scope, 'L1L2Regularizer'):
weight_l1_t = tf.convert_to_tensor(weight_l1,
dtype=tensor.dtype.base_dtype,
name='weight_l1')
weight_l2_t = tf.convert_to_tensor(weight_l2,
dtype=tensor.dtype.base_dtype,
name='weight_l2')
reg_l1 = tf.mul(weight_l1_t, tf.reduce_sum(tf.abs(tensor)),
name='value_l1')
reg_l2 = tf.mul(weight_l2_t, tf.nn.l2_loss(tensor),
name='value_l2')
return tf.add(reg_l1, reg_l2, name='value')
return regularizer
Example #7
| Source File: losses.py From deeplearning-benchmark with Apache License 2.0 | 6 votes |
|
def l2_loss(tensor, weight=1.0, scope=None):
"""Define a L2Loss, useful for regularize, i.e. weight decay.
Args:
tensor: tensor to regularize.
weight: an optional weight to modulate the loss.
scope: Optional scope for op_scope.
Returns:
the L2 loss op.
"""
with tf.op_scope([tensor], scope, 'L2Loss'):
weight = tf.convert_to_tensor(weight,
dtype=tensor.dtype.base_dtype,
name='loss_weight')
loss = tf.mul(weight, tf.nn.l2_loss(tensor), name='value')
tf.add_to_collection(LOSSES_COLLECTION, loss)
return loss
Example #8
| Source File: ops.py From deeplearning-benchmark with Apache License 2.0 | 6 votes |
|
def one_hot_encoding(labels, num_classes, scope=None):
"""Transform numeric labels into onehot_labels.
Args:
labels: [batch_size] target labels.
num_classes: total number of classes.
scope: Optional scope for op_scope.
Returns:
one hot encoding of the labels.
"""
with tf.op_scope([labels], scope, 'OneHotEncoding'):
batch_size = labels.get_shape()[0]
indices = tf.expand_dims(tf.range(0, batch_size), 1)
labels = tf.cast(tf.expand_dims(labels, 1), indices.dtype)
concated = tf.concat(1, [indices, labels])
onehot_labels = tf.sparse_to_dense(
concated, tf.pack([batch_size, num_classes]), 1.0, 0.0)
onehot_labels.set_shape([batch_size, num_classes])
return onehot_labels
Example #9
| Source File: ops.py From deeplearning-benchmark with Apache License 2.0 | 6 votes |
|
def dropout(inputs, keep_prob=0.5, is_training=True, scope=None):
"""Returns a dropout layer applied to the input.
Args:
inputs: the tensor to pass to the Dropout layer.
keep_prob: the probability of keeping each input unit.
is_training: whether or not the model is in training mode. If so, dropout is
applied and values scaled. Otherwise, inputs is returned.
scope: Optional scope for op_scope.
Returns:
a tensor representing the output of the operation.
"""
if is_training and keep_prob > 0:
with tf.op_scope([inputs], scope, 'Dropout'):
return tf.nn.dropout(inputs, keep_prob)
else:
return inputs
Example #10
| Source File: ops.py From deeplearning-benchmark with Apache License 2.0 | 6 votes |
|
def flatten(inputs, scope=None):
"""Flattens the input while maintaining the batch_size.
Assumes that the first dimension represents the batch.
Args:
inputs: a tensor of size [batch_size, ...].
scope: Optional scope for op_scope.
Returns:
a flattened tensor with shape [batch_size, k].
Raises:
ValueError: if inputs.shape is wrong.
"""
if len(inputs.get_shape()) < 2:
raise ValueError('Inputs must be have a least 2 dimensions')
dims = inputs.get_shape()[1:]
k = dims.num_elements()
with tf.op_scope([inputs], scope, 'Flatten'):
return tf.reshape(inputs, [-1, k])
Example #11
| Source File: image_processing.py From deeplearning-benchmark with Apache License 2.0 | 6 votes |
|
def eval_image(image, height, width, scope=None):
"""Prepare one image for evaluation.
Args:
image: 3-D float Tensor
height: integer
width: integer
scope: Optional scope for op_scope.
Returns:
3-D float Tensor of prepared image.
"""
with tf.op_scope([image, height, width], scope, 'eval_image'):
# Crop the central region of the image with an area containing 87.5% of
# the original image.
image = tf.image.central_crop(image, central_fraction=0.875)
# Resize the image to the original height and width.
image = tf.expand_dims(image, 0)
image = tf.image.resize_bilinear(image, [height, width],
align_corners=False)
image = tf.squeeze(image, [0])
return image
Example #12
| Source File: preprocessing.py From deeplearning-benchmark with Apache License 2.0 | 6 votes |
|
def decode_jpeg(image_buffer, scope=None): # , dtype=tf.float32):
"""Decode a JPEG string into one 3-D float image Tensor.
Args:
image_buffer: scalar string Tensor.
scope: Optional scope for op_scope.
Returns:
3-D float Tensor with values ranging from [0, 1).
"""
# with tf.op_scope([image_buffer], scope, 'decode_jpeg'):
# with tf.name_scope(scope, 'decode_jpeg', [image_buffer]):
with tf.name_scope(scope or 'decode_jpeg'):
# Decode the string as an RGB JPEG.
# Note that the resulting image contains an unknown height and width
# that is set dynamically by decode_jpeg. In other words, the height
# and width of image is unknown at compile-time.
image = tf.image.decode_jpeg(image_buffer, channels=3,
fancy_upscaling=False,
dct_method='INTEGER_FAST')
# image = tf.Print(image, [tf.shape(image)], 'Image shape: ')
return image
Example #13
| Source File: image_processing.py From terngrad with Apache License 2.0 | 6 votes |
|
def decode_raw(image_buffer, orig_height, orig_width, scope=None):
"""Decode a RAW string into one 3-D float image Tensor.
Args:
image_buffer: scalar string Tensor.
[orig_height, orig_width]: the size of original image
scope: Optional scope for op_scope.
Returns:
3-D float Tensor with values ranging from [0, 1).
"""
with tf.op_scope([image_buffer], scope, 'decode_raw'):
# Decode the string as an raw RGB.
image = tf.decode_raw(image_buffer, tf.uint8)
image = tf.reshape(image, tf.concat([orig_height,orig_width,[3]],0))
# After this point, all image pixels reside in [0,1)
# The various adjust_* ops all require this range for dtype float.
image = tf.image.convert_image_dtype(image, dtype=tf.float32)
return image
Example #14
| Source File: image_processing.py From terngrad with Apache License 2.0 | 6 votes |
|
def decode_jpeg(image_buffer, scope=None):
"""Decode a JPEG string into one 3-D float image Tensor.
Args:
image_buffer: scalar string Tensor.
scope: Optional scope for op_scope.
Returns:
3-D float Tensor with values ranging from [0, 1).
"""
with tf.op_scope([image_buffer], scope, 'decode_jpeg'):
# Decode the string as an RGB JPEG.
# Note that the resulting image contains an unknown height and width
# that is set dynamically by decode_jpeg. In other words, the height
# and width of image is unknown at compile-time.
image = tf.image.decode_jpeg(image_buffer, channels=3)
# After this point, all image pixels reside in [0,1)
# until the very end, when they're rescaled to (-1, 1). The various
# adjust_* ops all require this range for dtype float.
image = tf.image.convert_image_dtype(image, dtype=tf.float32)
return image
Example #15
| Source File: image_processing.py From terngrad with Apache License 2.0 | 6 votes |
|
def decode_png(image_buffer, scope=None):
"""Decode a JPEG string into one 3-D float image Tensor.
Args:
image_buffer: scalar string Tensor.
scope: Optional scope for op_scope.
Returns:
3-D float Tensor with values ranging from [0, 1).
"""
with tf.op_scope([image_buffer], scope, 'decode_png'):
# Decode the string as an RGB JPEG.
# Note that the resulting image contains an unknown height and width
# that is set dynamically by decode_jpeg. In other words, the height
# and width of image is unknown at compile-time.
image = tf.image.decode_png(image_buffer, channels=0)
# After this point, all image pixels reside in [0,1)
# until the very end, when they're rescaled to (-1, 1). The various
# adjust_* ops all require this range for dtype float.
image = tf.image.convert_image_dtype(image, dtype=tf.float32)
return image
Example #16
| Source File: losses.py From deeplearning-benchmark with Apache License 2.0 | 6 votes |
|
def l1_loss(tensor, weight=1.0, scope=None):
"""Define a L1Loss, useful for regularize, i.e. lasso.
Args:
tensor: tensor to regularize.
weight: scale the loss by this factor.
scope: Optional scope for op_scope.
Returns:
the L1 loss op.
"""
with tf.op_scope([tensor], scope, 'L1Loss'):
weight = tf.convert_to_tensor(weight,
dtype=tensor.dtype.base_dtype,
name='loss_weight')
loss = tf.mul(weight, tf.reduce_sum(tf.abs(tensor)), name='value')
tf.add_to_collection(LOSSES_COLLECTION, loss)
return loss
Example #17
| Source File: image_processing.py From terngrad with Apache License 2.0 | 6 votes |
|
def eval_alexnet_image(image, height, width, scope=None):
"""Prepare one image for evaluation.
Args:
image: 3-D float Tensor
height: integer
width: integer
scope: Optional scope for op_scope.
Returns:
3-D float Tensor of prepared image.
"""
with tf.op_scope([image, height, width], scope, 'eval_image'):
image = tf.image.resize_images(image, [_RESIZE_SIDE, _RESIZE_SIDE])
# Crop the central region of the image
image = tf.image.resize_image_with_crop_or_pad(image, height, width)
# scale and reduce mean
image = tf.multiply(image, 255.0)
image.set_shape([height, width, 3])
image = _mean_image_subtraction(image, [_R_MEAN, _G_MEAN, _B_MEAN])
return image
Example #18
| Source File: utils.py From tf-imagenet with Apache License 2.0 | 6 votes |
|
def decode_jpeg(image_buffer, scope=None): # , dtype=tf.float32):
"""Decode a JPEG string into one 3-D float image Tensor.
Args:
image_buffer: scalar string Tensor.
scope: Optional scope for op_scope.
Returns:
3-D float Tensor with values ranging from [0, 1).
"""
# with tf.op_scope([image_buffer], scope, 'decode_jpeg'):
# with tf.name_scope(scope, 'decode_jpeg', [image_buffer]):
with tf.name_scope(scope or 'decode_jpeg'):
# Decode the string as an RGB JPEG.
# Note that the resulting image contains an unknown height and width
# that is set dynamically by decode_jpeg. In other words, the height
# and width of image is unknown at compile-time.
image = tf.image.decode_jpeg(image_buffer, channels=3,
fancy_upscaling=False,
dct_method='INTEGER_FAST')
# image = tf.Print(image, [tf.shape(image)], 'Image shape: ')
return image
Example #19
| Source File: losses.py From piecewisecrf with MIT License | 6 votes |
|
def l1_regularizer(weight=1.0, scope=None):
"""Define a L1 regularizer.
Args:
weight: scale the loss by this factor.
scope: Optional scope for op_scope.
Returns:
a regularizer function.
"""
def regularizer(tensor):
with tf.op_scope([tensor], scope, 'L1Regularizer'):
l1_weight = tf.convert_to_tensor(weight,
dtype=tensor.dtype.base_dtype,
name='weight')
return tf.mul(l1_weight, tf.reduce_sum(tf.abs(tensor)), name='value')
return regularizer
Example #20
| Source File: losses.py From piecewisecrf with MIT License | 6 votes |
|
def l2_regularizer(weight=1.0, scope=None):
"""Define a L2 regularizer.
Args:
weight: scale the loss by this factor.
scope: Optional scope for op_scope.
Returns:
a regularizer function.
"""
def regularizer(tensor):
with tf.op_scope([tensor], scope, 'L2Regularizer'):
l2_weight = tf.convert_to_tensor(weight,
dtype=tensor.dtype.base_dtype,
name='weight')
return tf.mul(l2_weight, tf.nn.l2_loss(tensor), name='value')
return regularizer
Example #21
| Source File: losses.py From piecewisecrf with MIT License | 6 votes |
|
def l1_l2_regularizer(weight_l1=1.0, weight_l2=1.0, scope=None):
"""Define a L1L2 regularizer.
Args:
weight_l1: scale the L1 loss by this factor.
weight_l2: scale the L2 loss by this factor.
scope: Optional scope for op_scope.
Returns:
a regularizer function.
"""
def regularizer(tensor):
with tf.op_scope([tensor], scope, 'L1L2Regularizer'):
weight_l1_t = tf.convert_to_tensor(weight_l1,
dtype=tensor.dtype.base_dtype,
name='weight_l1')
weight_l2_t = tf.convert_to_tensor(weight_l2,
dtype=tensor.dtype.base_dtype,
name='weight_l2')
reg_l1 = tf.mul(weight_l1_t, tf.reduce_sum(tf.abs(tensor)),
name='value_l1')
reg_l2 = tf.mul(weight_l2_t, tf.nn.l2_loss(tensor),
name='value_l2')
return tf.add(reg_l1, reg_l2, name='value')
return regularizer
Example #22
| Source File: losses.py From piecewisecrf with MIT License | 6 votes |
|
def l1_loss(tensor, weight=1.0, scope=None):
"""Define a L1Loss, useful for regularize, i.e. lasso.
Args:
tensor: tensor to regularize.
weight: scale the loss by this factor.
scope: Optional scope for op_scope.
Returns:
the L1 loss op.
"""
with tf.op_scope([tensor], scope, 'L1Loss'):
weight = tf.convert_to_tensor(weight,
dtype=tensor.dtype.base_dtype,
name='loss_weight')
loss = tf.mul(weight, tf.reduce_sum(tf.abs(tensor)), name='value')
tf.add_to_collection(LOSSES_COLLECTION, loss)
return loss
Example #23
| Source File: losses.py From piecewisecrf with MIT License | 6 votes |
|
def l2_loss(tensor, weight=1.0, scope=None):
"""Define a L2Loss, useful for regularize, i.e. weight decay.
Args:
tensor: tensor to regularize.
weight: an optional weight to modulate the loss.
scope: Optional scope for op_scope.
Returns:
the L2 loss op.
"""
with tf.op_scope([tensor], scope, 'L2Loss'):
weight = tf.convert_to_tensor(weight,
dtype=tensor.dtype.base_dtype,
name='loss_weight')
loss = tf.mul(weight, tf.nn.l2_loss(tensor), name='value')
tf.add_to_collection(LOSSES_COLLECTION, loss)
return loss
Example #24
| Source File: ops.py From piecewisecrf with MIT License | 6 votes |
|
def one_hot_encoding(labels, num_classes, scope=None):
"""Transform numeric labels into onehot_labels.
Args:
labels: [batch_size] target labels.
num_classes: total number of classes.
scope: Optional scope for op_scope.
Returns:
one hot encoding of the labels.
"""
with tf.op_scope([labels], scope, 'OneHotEncoding'):
batch_size = labels.get_shape()[0]
indices = tf.expand_dims(tf.range(0, batch_size), 1)
labels = tf.cast(tf.expand_dims(labels, 1), indices.dtype)
concated = tf.concat(1, [indices, labels])
onehot_labels = tf.sparse_to_dense(
concated, tf.pack([batch_size, num_classes]), 1.0, 0.0)
onehot_labels.set_shape([batch_size, num_classes])
return onehot_labels
Example #25
| Source File: ops.py From piecewisecrf with MIT License | 6 votes |
|
def dropout(inputs, keep_prob=0.5, is_training=True, scope=None):
"""Returns a dropout layer applied to the input.
Args:
inputs: the tensor to pass to the Dropout layer.
keep_prob: the probability of keeping each input unit.
is_training: whether or not the model is in training mode. If so, dropout is
applied and values scaled. Otherwise, inputs is returned.
scope: Optional scope for op_scope.
Returns:
a tensor representing the output of the operation.
"""
if is_training and keep_prob > 0:
with tf.op_scope([inputs], scope, 'Dropout'):
return tf.nn.dropout(inputs, keep_prob)
else:
return inputs
Example #26
| Source File: ops.py From piecewisecrf with MIT License | 6 votes |
|
def flatten(inputs, scope=None):
"""Flattens the input while maintaining the batch_size.
Assumes that the first dimension represents the batch.
Args:
inputs: a tensor of size [batch_size, ...].
scope: Optional scope for op_scope.
Returns:
a flattened tensor with shape [batch_size, k].
Raises:
ValueError: if inputs.shape is wrong.
"""
if len(inputs.get_shape()) < 2:
raise ValueError('Inputs must be have a least 2 dimensions')
dims = inputs.get_shape()[1:]
k = dims.num_elements()
with tf.op_scope([inputs], scope, 'Flatten'):
return tf.reshape(inputs, [-1, k])
Example #27
| Source File: losses.py From Action_Recognition_Zoo with MIT License | 6 votes |
|
def l2_regularizer(weight=1.0, scope=None):
"""Define a L2 regularizer.
Args:
weight: scale the loss by this factor.
scope: Optional scope for op_scope.
Returns:
a regularizer function.
"""
def regularizer(tensor):
with tf.op_scope([tensor], scope, 'L2Regularizer'):
l2_weight = tf.convert_to_tensor(weight,
dtype=tensor.dtype.base_dtype,
name='weight')
return tf.mul(l2_weight, tf.nn.l2_loss(tensor), name='value')
return regularizer
Example #28
| Source File: losses.py From Action_Recognition_Zoo with MIT License | 6 votes |
|
def l1_l2_regularizer(weight_l1=1.0, weight_l2=1.0, scope=None):
"""Define a L1L2 regularizer.
Args:
weight_l1: scale the L1 loss by this factor.
weight_l2: scale the L2 loss by this factor.
scope: Optional scope for op_scope.
Returns:
a regularizer function.
"""
def regularizer(tensor):
with tf.op_scope([tensor], scope, 'L1L2Regularizer'):
weight_l1_t = tf.convert_to_tensor(weight_l1,
dtype=tensor.dtype.base_dtype,
name='weight_l1')
weight_l2_t = tf.convert_to_tensor(weight_l2,
dtype=tensor.dtype.base_dtype,
name='weight_l2')
reg_l1 = tf.mul(weight_l1_t, tf.reduce_sum(tf.abs(tensor)),
name='value_l1')
reg_l2 = tf.mul(weight_l2_t, tf.nn.l2_loss(tensor),
name='value_l2')
return tf.add(reg_l1, reg_l2, name='value')
return regularizer
Example #29
| Source File: losses.py From Action_Recognition_Zoo with MIT License | 6 votes |
|
def l1_loss(tensor, weight=1.0, scope=None):
"""Define a L1Loss, useful for regularize, i.e. lasso.
Args:
tensor: tensor to regularize.
weight: scale the loss by this factor.
scope: Optional scope for op_scope.
Returns:
the L1 loss op.
"""
with tf.op_scope([tensor], scope, 'L1Loss'):
weight = tf.convert_to_tensor(weight,
dtype=tensor.dtype.base_dtype,
name='loss_weight')
loss = tf.mul(weight, tf.reduce_sum(tf.abs(tensor)), name='value')
tf.add_to_collection(LOSSES_COLLECTION, loss)
return loss
Example #30
| Source File: losses.py From Action_Recognition_Zoo with MIT License | 6 votes |
|
def l2_loss(tensor, weight=1.0, scope=None):
"""Define a L2Loss, useful for regularize, i.e. weight decay.
Args:
tensor: tensor to regularize.
weight: an optional weight to modulate the loss.
scope: Optional scope for op_scope.
Returns:
the L2 loss op.
"""
with tf.op_scope([tensor], scope, 'L2Loss'):
weight = tf.convert_to_tensor(weight,
dtype=tensor.dtype.base_dtype,
name='loss_weight')
loss = tf.mul(weight, tf.nn.l2_loss(tensor), name='value')
tf.add_to_collection(LOSSES_COLLECTION, loss)
return loss
