Computes the gradient of nearest neighbor interpolation.

    grads, size, align_corners=False, half_pixel_centers=False, name=None


  • grads: A Tensor. Must be one of the following types: uint8, int8, int32, half, float32, float64. 4-D with shape [batch, height, width, channels].
  • size: A 1-D int32 Tensor of 2 elements: orig_height, orig_width. The original input size.
  • align_corners: An optional bool. Defaults to False. If true, the centers of the 4 corner pixels of the input and grad tensors are aligned. Defaults to false.
  • half_pixel_centers: An optional bool. Defaults to False.
  • name: A name for the operation (optional).


A Tensor. Has the same type as grads.