The training can not run

[wangpichao]

/PatchVisionTransformer/deit/models.py", line 232, in similarity
high_order = (patches.mean(dim=(2, 3), deepdim=True) - patches / (img_size ** 2)) * (img_size ** 2) / (img_size ** 2 - 1)
TypeError: mean() received an invalid combination of arguments - got (deepdim=bool, dim=tuple, ), but expected one of:

• (*, torch.dtype dtype)
  didn't match because some of the keywords were incorrect: deepdim, dim
• (tuple of names dim, bool keepdim, *, torch.dtype dtype)
• (tuple of ints dim, bool keepdim, *, torch.dtype dtype)

[ChengyueGongR]

Thanks for your information. It should be changed into `patches.mean(dim=(2, 3), deepdim=True))'

[wangpichao]

Thanks for your information. It should be changed into `patches.mean(dim=(2, 3), deepdim=True))'

In fact, your release codes have other errors, and I suggest you run the released codes again to make sure it is runable. Thanks.

[ChengyueGongR]

Thanks for your advice. The issues are caused by the `similarity function.