Ming Li

> Hi @mitming! I think you can use [my fork version of this repo](https://github.com/SunQpark/pytorch-template), which implements many useful features including DDP. Thanks a lot! I will tri it!

> Yes, we've discussed data processing acceleration before, but we think it is not a high-priority plan. However, if you have any plans, feel free to create PR. Hi @zhouzaida...

> Hi @Pilhyeon, thanks for your great work! Now I'm following your BMUE and have some trouble in reproducing the results on ActivityNet dataset. > > I have tried to...

> how about the settings of 'class_th', 'act_thresh_cas', 'act_thresh_magnitudes'? > Could you provide a complete configure file for ActivityNet1.2 and ActivityNet1.3? > That will very helpful.@kiwiJ Hi, could you reproduce...

> > > how about the settings of 'class_th', 'act_thresh_cas', 'act_thresh_magnitudes'? > > > Could you provide a complete configure file for ActivityNet1.2 and ActivityNet1.3? > > > That will...

> Hi, what hardware are you using ? > It looks like you have different GPU and that the module is only built for the first gpu, which is not...

> Ok so this is not this problem. > > I just tested your code with my computer, that has 1 1080 Ti and I didn't get the "segmentation fault"...

hi @ClementPinard , I try to install PyTorch 1.7.1, and then use pip to install the tool, there is no warnning or error during installation, but I cannot import this...

When I use pytorch 1.1 and install via `python setup.py install`, there is another error: ``` Traceback (most recent call last): File "", line 1, in File "/home/liming/anaconda3/envs/1/lib/python3.7/site-packages/spatial_correlation_sampler-0.3.0-py3.7-linux-x86_64.egg/spatial_correlation_sampler/__init__.py", line 1,...

> Hi, I agree that mixup could be regarded as a regularization method and requires longer training epochs to make the training process converge. We are so sorry that we...