chunyan

Results 5 comments of chunyan

I want to install torch1.7.0 , my cuda is 11.3, pip list ``` Package Version ------------------ --------- addict 2.4.0 certifi 2022.6.15 charset-normalizer 2.1.1 click 8.1.3 colorama 0.4.5 commonmark 0.9.1 idna...

The only way can slove it I thought is to change a computer or a gpu. I wonder if there are other ways. I want to use the light version...

After that, I try it using qpt(https://github.com/QPT-Family/QPT),problem also occurs. it occurs as: `ck (most recent call last): File "D:\software\program\Anaconda3\envs\open-mmlab2\lib\runpy.py", line 197, in _run_module_as_main return _run_code(code, main_globals, None, File "D:\software\program\Anaconda3\envs\open-mmlab2\lib\runpy.py", line...

The origin [code](https://github.com/facebookresearch/SlowFast/blob/main/slowfast/models/batchnorm_helper.py) like this: ``` def forward(self, x): if self.training: n, c, t, h, w = x.shape x = x.view(n // self.num_splits, c * self.num_splits, t, h, w) x...