numpy broadcasting semantic

Creator

Creator

Seonglae Cho

Created

Created

2023 May 25 6:15

Editor

Editor

Seonglae Cho

Edited

Edited

2023 Aug 19 8:50

Refs

Refs

data copy 없이

In-place semantics

broadcasting에 따라 in-place tensor의 모양이 변경되지 않는다

notion image

1차원은 broadcasting되는데 2차원부터 안되니까 1차원만 되는 이유

차원 없다면 뒤부터 둔다

notion image

즉 위 첫 케이스에서 3을 중간에 둘 수 없다

Backwards compatibility

How does pytorch broadcasting work?

torch.add(torch.ones(4,1), torch.randn(4)) produces a Tensor with size: torch.Size([4,4]). Can someone provide a logic behind this?

How does pytorch broadcasting work?

https://stackoverflow.com/questions/51371070/how-does-pytorch-broadcasting-work

How does pytorch broadcasting work?

pytorch broadcasting

Many PyTorch operations support NumPy's broadcasting semantics. what is broadcasting? NumPy docs에 공식설명은 아래와 같다. broadcasting Reference https://pytorc

pytorch broadcasting

https://velog.io/@optjyy/pytorch-broad-casting

pytorch broadcasting

Recommendations

///////