Zhuofei Kang

> Do you train QueryInst on COCO? thank you for your reply. No, I train it on my dataset. And I think the dataset is ok because I trained maskrcnn...

> I suggest you can try to tune the lr, warmup lr and other hyperparameters. Can you successfully train Sparse R-CNN on your dataset? I didn't try with Sparse R-CNN....

> I suggest you try to tune Sparse R-CNN first, the query-based approaches are much less robust than Faster / Mask R-CNN in term of training and optimization. ok, I...

have you solved this error?

the reason is the pytorch and cuda version, it works well now.

> You can follow the instructions [here](https://pytorch.org/get-started/previous-versions/) to install PyTorch 0.4.1 w/ CUDA 9.0. hello, when I install it, there will be a error. Can you help me? Thank you!...

> 如果大家可以用中文交流或许可以减少一些沟通成本... 你好，我现在有这个error，请问你知道是什么原因吗？我的transformers是4.28.0.dev0 ``` [2023-06-01 09:44:26,442] [INFO] [comm.py:622:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl [2023-06-01 09:44:38,504] [INFO] [partition_parameters.py:454:__exit__] finished initializing model with 6.74B parameters Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 33/33...

> Write your dataset similar as data/ThreeDMatch.py#L11, and new your_dataset.yaml file similar as configs/threedmatch.yaml. > > Then maybe you are ready to train with minor modifications. > > Good luck....

> > > Write your dataset similar as data/ThreeDMatch.py#L11, and new your_dataset.yaml file similar as configs/threedmatch.yaml. > > > Then maybe you are ready to train with minor modifications. >...

> > > > > Write your dataset similar as data/ThreeDMatch.py#L11, and new your_dataset.yaml file similar as configs/threedmatch.yaml. > > > > > Then maybe you are ready to train...