oneflow.nn.functional.fold

oneflow.nn.functional.fold(input, output_size, kernel_size, dilation=1, padding=0, stride=1)

The documentation is referenced from: https://pytorch.org/docs/1.10/generated/torch.nn.functional.fold.html.

Combines an array of sliding local blocks into a large containing tensor.

Warning

Currently, only 3-D input tensors (batched image-like tensors) are supported, and only unbatched (3D) or batched (4D) image-like output tensors are supported.

See oneflow.nn.Fold for details.