tf.raw_ops.StridedSliceGrad

Returns the gradient of StridedSlice.

Since StridedSlice cuts out pieces of its input which is size shape, its gradient will have the same shape (which is passed here as shape). The gradient will be zero in any element that the slice does not select.

Arguments are the same as StridedSliceGrad with the exception that dy is the input gradient to be propagated and shape is the shape of StridedSlice's input.

Args
shape A Tensor. Must be one of the following types: int32, int64.
begin A Tensor. Must have the same type as shape.
end A Tensor. Must have the same type as shape.
strides A Tensor. Must have the same type as shape.
dy A Tensor.
begin_mask An optional int. Defaults to 0.
end_mask An optional int. Defaults to 0.
ellipsis_mask An optional int. Defaults to 0.
new_axis_mask An optional int. Defaults to 0.
shrink_axis_mask An optional int. Defaults to 0.
name A name for the operation (optional).
Returns
A Tensor. Has the same type as dy.

© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r2.4/api_docs/python/tf/raw_ops/StridedSliceGrad