Python tensorflow.python.ops.gen_image_ops.crop_and_resize_grad_image() Examples
The following are 5
code examples of tensorflow.python.ops.gen_image_ops.crop_and_resize_grad_image().
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.python.ops.gen_image_ops
, or try the search function
.
.
Example #1
| Source File: image_grad.py From lambda-packs with MIT License | 5 votes |
|
def _CropAndResizeGrad(op, grad):
"""The derivatives for crop_and_resize.
We back-propagate to the image only when the input image tensor has floating
point dtype but we always back-propagate to the input boxes tensor.
Args:
op: The CropAndResize op.
grad: The tensor representing the gradient w.r.t. the output.
Returns:
The gradients w.r.t. the input image, boxes, as well as the always-None
gradients w.r.t. box_ind and crop_size.
"""
image = op.inputs[0]
if image.get_shape().is_fully_defined():
image_shape = image.get_shape().as_list()
else:
image_shape = array_ops.shape(image)
allowed_types = [dtypes.float16, dtypes.float32, dtypes.float64]
if op.inputs[0].dtype in allowed_types:
# pylint: disable=protected-access
grad0 = gen_image_ops.crop_and_resize_grad_image(grad,
op.inputs[1],
op.inputs[2],
image_shape,
T=op.get_attr("T"))
# pylint: enable=protected-access
else:
grad0 = None
grad1 = gen_image_ops.crop_and_resize_grad_boxes(grad, op.inputs[0],
op.inputs[1], op.inputs[2])
return [grad0, grad1, None, None]
Example #2
| Source File: image_grad.py From auto-alt-text-lambda-api with MIT License | 5 votes |
|
def _CropAndResizeGrad(op, grad):
"""The derivatives for crop_and_resize.
We back-propagate to the image only when the input image tensor has floating
point dtype but we always back-propagate to the input boxes tensor.
Args:
op: The CropAndResize op.
grad: The tensor representing the gradient w.r.t. the output.
Returns:
The gradients w.r.t. the input image, boxes, as well as the always-None
gradients w.r.t. box_ind and crop_size.
"""
image = op.inputs[0]
if image.get_shape().is_fully_defined():
image_shape = image.get_shape().as_list()
else:
image_shape = array_ops.shape(image)
allowed_types = [dtypes.float16, dtypes.float32, dtypes.float64]
if op.inputs[0].dtype in allowed_types:
# pylint: disable=protected-access
grad0 = gen_image_ops.crop_and_resize_grad_image(grad,
op.inputs[1],
op.inputs[2],
image_shape,
T=op.get_attr("T"))
# pylint: enable=protected-access
else:
grad0 = None
grad1 = gen_image_ops.crop_and_resize_grad_boxes(grad, op.inputs[0],
op.inputs[1], op.inputs[2])
return [grad0, grad1, None, None]
Example #3
| Source File: image_grad.py From deep_image_model with Apache License 2.0 | 5 votes |
|
def _CropAndResizeGrad(op, grad):
"""The derivatives for crop_and_resize.
We back-propagate to the image only when the input image tensor has floating
point dtype but we always back-propagate to the input boxes tensor.
Args:
op: The CropAndResize op.
grad: The tensor representing the gradient w.r.t. the output.
Returns:
The gradients w.r.t. the input image, boxes, as well as the always-None
gradients w.r.t. box_ind and crop_size.
"""
image = op.inputs[0]
if image.get_shape().is_fully_defined():
image_shape = image.get_shape().as_list()
else:
image_shape = array_ops.shape(image)
allowed_types = [dtypes.float16, dtypes.float32, dtypes.float64]
if op.inputs[0].dtype in allowed_types:
# pylint: disable=protected-access
grad0 = gen_image_ops.crop_and_resize_grad_image(grad,
op.inputs[1],
op.inputs[2],
image_shape,
T=op.get_attr("T"))
# pylint: enable=protected-access
else:
grad0 = None
grad1 = gen_image_ops.crop_and_resize_grad_boxes(grad, op.inputs[0],
op.inputs[1], op.inputs[2])
return [grad0, grad1, None, None]
Example #4
| Source File: image_grad.py From Serverless-Deep-Learning-with-TensorFlow-and-AWS-Lambda with MIT License | 5 votes |
|
def _CropAndResizeGrad(op, grad):
"""The derivatives for crop_and_resize.
We back-propagate to the image only when the input image tensor has floating
point dtype but we always back-propagate to the input boxes tensor.
Args:
op: The CropAndResize op.
grad: The tensor representing the gradient w.r.t. the output.
Returns:
The gradients w.r.t. the input image, boxes, as well as the always-None
gradients w.r.t. box_ind and crop_size.
"""
image = op.inputs[0]
if image.get_shape().is_fully_defined():
image_shape = image.get_shape().as_list()
else:
image_shape = array_ops.shape(image)
allowed_types = [dtypes.float16, dtypes.float32, dtypes.float64]
if op.inputs[0].dtype in allowed_types:
# pylint: disable=protected-access
grad0 = gen_image_ops.crop_and_resize_grad_image(grad,
op.inputs[1],
op.inputs[2],
image_shape,
T=op.get_attr("T"))
# pylint: enable=protected-access
else:
grad0 = None
grad1 = gen_image_ops.crop_and_resize_grad_boxes(grad, op.inputs[0],
op.inputs[1], op.inputs[2])
return [grad0, grad1, None, None]
Example #5
| Source File: image_grad.py From keras-lambda with MIT License | 5 votes |
|
def _CropAndResizeGrad(op, grad):
"""The derivatives for crop_and_resize.
We back-propagate to the image only when the input image tensor has floating
point dtype but we always back-propagate to the input boxes tensor.
Args:
op: The CropAndResize op.
grad: The tensor representing the gradient w.r.t. the output.
Returns:
The gradients w.r.t. the input image, boxes, as well as the always-None
gradients w.r.t. box_ind and crop_size.
"""
image = op.inputs[0]
if image.get_shape().is_fully_defined():
image_shape = image.get_shape().as_list()
else:
image_shape = array_ops.shape(image)
allowed_types = [dtypes.float16, dtypes.float32, dtypes.float64]
if op.inputs[0].dtype in allowed_types:
# pylint: disable=protected-access
grad0 = gen_image_ops.crop_and_resize_grad_image(grad,
op.inputs[1],
op.inputs[2],
image_shape,
T=op.get_attr("T"))
# pylint: enable=protected-access
else:
grad0 = None
grad1 = gen_image_ops.crop_and_resize_grad_boxes(grad, op.inputs[0],
op.inputs[1], op.inputs[2])
return [grad0, grad1, None, None]
