yukang

Hi, I think this might be caused from that the voxel features in some frames are very few. I think you can add a line of `continue` to skip the...

voxelnext_nuscenes_kernel1.pth https://pan.baidu.com/s/1SSvIIQpafZmhFXoEI2AjYQ 提取码: x4d9 VoxelNeXt_Argo2.pth https://pan.baidu.com/s/1Fw-uWVl2dCsx_HvCr-NmmQ 提取码: kt9p

请问你测试用的脚本，和结果是多少？

您可以发一下完整的log，还有测试结果。

Sorry. As I have already leave the internship company, I did not download it from there before. Thus, I do not have it at this moment. It is not hard...

Sorry for the late reply. I thinks this issue might comes from the installation. Would you please show your torch and torchvision version?

Hi, sorry for missing this. It is here. https://drive.google.com/file/d/1br0VDamameu7B1G1p4HEjj6LshGs5dHB/view?usp=share_link

Hi, It should be as following. ``` def _ddp_dict(_dict): new_dict = {} for k in _dict: new_dict['module.' + k] = _dict[k] return new_dict ```

@ShaniGam @ckleban Try this one. [async_dqn.txt](https://github.com/coreylynch/async-rl/files/1144794/async_dqn.txt)

@enragedginger Sorry, the code is not written by me. I found it from a blog.... So I don't have right to do this with other's code. @Mageswaran1989 In my opinion,...