torch.Tensor.repeat#

Tensor.repeat(*repeats)→Tensor#

Repeats this tensor along the specified dimensions.

Unlikeexpand(), this function copies the tensor’s data.

Warning

repeat() behaves differently fromnumpy.repeat,but is more similar tonumpy.tile.For the operator similar tonumpy.repeat, seetorch.repeat_interleave().

Parameters

repeat (torch.Size,int...,tuple ofint orlist ofint) – The number of times to repeat this tensor along each dimension

Example:

>>>x=torch.tensor([1,2,3])>>>x.repeat(4,2)tensor([[ 1,  2,  3,  1,  2,  3],        [ 1,  2,  3,  1,  2,  3],        [ 1,  2,  3,  1,  2,  3],        [ 1,  2,  3,  1,  2,  3]])>>>x.repeat(4,2,1).size()torch.Size([4, 2, 3])