|TensorFlow 1 version||View source on GitHub|
Returns image gradients (dy, dx) for each color channel.
Compat aliases for migration
See Migration guide for more details.
tf.image.image_gradients( image )
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.
||Tensor with shape [batch_size, h, w, d].|
|Pair of tensors (dy, dx) holding the vertical and horizontal image gradients (1-step finite difference).|