Di Wu

@pengwangucla @XibinSong Hi, Yes. I think the mesh problem is solved. However, there is a new issue in term of using camera intrinsic in the code. I have made an...

@Jerrypiglet Hi Jerry. No, unfortunately I didn't manage to fix the GLEW issue. So in the end, I didn't use the provided render at all. Cheers

> > Nevertheless, after some examination, we found out that some car_id are rather different than the real car models, for example the closest car and the car under 40km/h...

@Tbarowski , Here is favor: Using your provided json file, we rendered the mesh as below which is different from what you get. I have cleaned up a script as:...

Hmm, actually I had modified the Pytorch lightning code to allow PyTorch lightning CLI to allow `strict=False` for my need and it works. Maybe I can contribute a PR these...

1. tensorboard 安装错误可能需要你自己巡查mmdet或者pytorch的安装文件了。或者你自己查看stackoverflow了， 这个错误我们没有遇到过。 2.- validation is only written for distributed training. If you only have a single gpu, you can do something like: `CUDA_VISIBLE_DEVICES=0 python -m torch.distributed.launch --nproc_per_node=1 train_kaggle_pku.py...

Hey, @whai362 your question is too vague. Those two lines require theano to compile the functions. It is very likely that the theano fail to compile the functions.

HI @SangbumChoi , from the `test_grounding_dino_loss`, you have the `"loss_ce_enc": torch.tensor(16226.3145),`: the scale of the loss is way to big from other loss? Isn't the trained network should have smaller...