全ての要素がlistで完結しているなら何も問題はないと思いますが、tensor in list -> tensorsの際にひっかかったため
なお、list内のtensorは全て同じshapeを持つとします。
arrs = [torch.Tensor(), torch.Tensor(), torch.Tensor(), ...]
arrs = torch.cat(arrs).reshape(len(arrs), *arrs[0].shape)
More than 3 years have passed since last update.
pyTorchでlist(torch.Tensor, torch.Tensor, ...)をtorch.Tensorにまとめる
Posted at
Register as a new user and use Qiita more conveniently
- You get articles that match your needs
- You can efficiently read back useful information
- You can use dark theme
List of users who liked
99