permute¶
- nvtripy.permute(input: Tensor, perm: Sequence[int]) Tensor [source]¶
Returns a tensor with its dimensions permuted.
- Parameters:
input (Tensor) – [dtype=T1] The input tensor.
perm (Sequence[int]) – The desired ordering of dimensions. It must contain all integers in \([0..N-1]\) exactly once, where \(N\) is the rank of the input tensor.
- Returns:
[dtype=T1] A new tensor.
- Return type:
Example
1input = tp.reshape(tp.arange(6, dtype=tp.float32), (2, 3)) 2output = tp.permute(input, (1, 0))
Local Variables¶>>> input tensor( [[0, 1, 2], [3, 4, 5]], dtype=float32, loc=gpu:0, shape=(2, 3)) >>> output tensor( [[0, 3], [1, 4], [2, 5]], dtype=float32, loc=gpu:0, shape=(3, 2))