Returns image gradients (dy, dx) for each color channel.
Both output tensors have the same shape as the input: [batch_size, h, w, d]. The gradient values are organized so that [I(x+1, y) - I(x, y)] is in location (x, y). That means that dy will always have zeros in the last row, and dx will always have zeros in the last column.
image: Tensor with shape [batch_size, h, w, d].
Pair of tensors (dy, dx) holding the vertical and horizontal image gradients (1-step finite difference).
imageis not a 4D tensor.
© 2018 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.