Hongkun Chen

I have a problem here https://github.com/microsoft/SoftTeacher/blob/bef9a256e5c920723280146fc66b82629b3ee9d4/ssod/models/soft_teacher.py#L224-L232 the `_score` here is actually labels? according to the [mmdet codes](https://github.com/open-mmlab/mmdetection/blob/c44a058edbc2974fa9f358a4b7815840e6d4777c/mmdet/models/roi_heads/standard_roi_head.py#L253-L254) ```python det_bboxes, det_labels = self.simple_test_bboxes( x, img_metas, proposal_list, self.test_cfg, rescale=rescale) ``` if so,...

I can't reach the results either. I only have 3 GPUs, so I can only try 8 & 12 batches. For 12 batches, I trained for 260 epochs, and for...

Solved this problem! It seems that I need to USE_ROAD_PLANE augmentation, reference to this [issue](https://github.com/open-mmlab/OpenPCDet/issues/483)

I had the same problem. But I found my datasets not strictly following this structure PointRCNN ├── data │ ├── KITTI │ │ ├── ImageSets │ │ ├── object │...

Similar to this [issue](https://github.com/pytorch/pytorch/issues/77737), which also offers some work around. It seems we would have to live with problem for a while, but acceptable😂

我现在所有视频都下载不了，会弹出一个新窗口  但什么都没发生...估计是B站更新了一波

This is not just happening on the Android SDK, I am using this on a CUDA device, but this error still happens. I tried to use a built from source...

@BenchuYee hi, I want to adjust the KVCache for more flexible usage, which old commit did you use to build the nn.KVCache model? and BTW, do you guys observe obvious...

This would work if you run the container and use the command line, but if you write a docker file and build the mpi4py inside the docker, it will give...