请求支持torch.roll和torch.flip

[Baiyuetribe]

error log | 日志或报错信息 | ログ

>>> x = torch.tensor([1, 2, 3, 4, 5, 6, 7, 8]).view(4, 2)
>>> x
tensor([[1, 2],
        [3, 4],
        [5, 6],
        [7, 8]])
>>> torch.roll(x, 1)
tensor([[8, 1],
        [2, 3],
        [4, 5],
        [6, 7]])
>>> torch.roll(x, 1, 0)
tensor([[7, 8],
        [1, 2],
        [3, 4],
        [5, 6]])

>>> x = torch.arange(8).view(2, 2, 2)
>>> x
tensor([[[ 0,  1],
         [ 2,  3]],

        [[ 4,  5],
         [ 6,  7]]])
>>> torch.flip(x, [0, 1])
tensor([[[ 6,  7],
         [ 4,  5]],

        [[ 2,  3],
         [ 0,  1]]])

[nihui]

https://github.com/Tencent/ncnn/pull/5623

[Baiyuetribe]

torch.topk等也支持一下呗，ncnn模型转换的泛化支持，真的很急。大部分新模型，都会卡在一两个op上，干着急

[zengjie617789]

是支持了么？ 还是显示不支持

[Baiyuetribe]

torch.roll支持了；torch.flip仍然不支持 @zengjie617789

[zengjie617789]

@Baiyuetribe 好的，谢谢。

[nihui]

https://github.com/Tencent/ncnn/pull/6233