On this page
torch.chunk
torch.chunk(input, chunks, dim=0) → List of Tensors
-
Attempts to split a tensor into the specified number of chunks. Each chunk is a view of the input tensor.
Note
This function may return fewer than the specified number of chunks!
See also
torch.tensor_split()
a function that always returns exactly the specified number of chunksIf the tensor size along the given dimension
dim
is divisible bychunks
, all returned chunks will be the same size. If the tensor size along the given dimensiondim
is not divisible bychunks
, all returned chunks will be the same size, except the last one. If such division is not possible, this function may return fewer than the specified number of chunks.- Parameters
Example
>>> torch.arange(11).chunk(6) (tensor([0, 1]), tensor([2, 3]), tensor([4, 5]), tensor([6, 7]), tensor([8, 9]), tensor([10])) >>> torch.arange(12).chunk(6) (tensor([0, 1]), tensor([2, 3]), tensor([4, 5]), tensor([6, 7]), tensor([8, 9]), tensor([10, 11])) >>> torch.arange(13).chunk(6) (tensor([0, 1, 2]), tensor([3, 4, 5]), tensor([6, 7, 8]), tensor([ 9, 10, 11]), tensor([12]))
© 2024, PyTorch Contributors
PyTorch has a BSD-style license, as found in the LICENSE file.
https://pytorch.org/docs/2.1/generated/torch.chunk.html