wmw

@lpasselin @mbusch-regis @shagren Is there any method to transform the depth image(*png) to point cloud ?

@shagren Thanks for your suggestion. I am really a freshman to the pyk4a. Another problem appears:is there any method to project the point cloud back to depth image?

@YanhaoZhang Thanks for your contributions and I follow your instructions, but unluckily, I get: UILD__ instead."" is not valid in preprocessor expressions #define __CUDACC_VER__ "__CUDACC_VER__ is no longer supported. Use...

Thanks @YanhaoZhang I have fixed all the bugs since I just reboot my computer and restart building all the programs.

When I run the code line ./build/bin/app /path/to/data /path/to/params with the umbrella data. It seems this is the only running output: iter. no. 900 iter. no. 950 iter. no. 1000...

@nic-stark I still have such problem when I want to use the screenshot. But I do not understand the "libs". Does it refer to some software?Besides, I also do not...

OK,this problem is solved by myself. I'd want to paste the solution! All the problems come from unsupported formats.The map type and shaped should be converted to the following format:...

@weigao95 @Algomorph When I run ./surfelwarp_app /test_data/boxing_config.json I get an error Segmentation fault (core dumped) I do not know the reason.

Firstly, in examples/images/diffusion/configs/Teyvat/train_colossalai_teyvat.yaml. If I change use_ema: True. Then I get error like: ``` /opt/conda/lib/python3.7/site-packages/torch/optim/lr_scheduler.py:136: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you should call...

Besides, in your readme, you tell that I need to use xformers0.0.12. However, in the code [https://github.com/hpcaitech/ColossalAI/blob/d4fb7bfda7a2da5480e1187e8d3e40884b42ba11/applications/Chat/coati/kernels/opt_attn.py#L72](https://github.com/hpcaitech/ColossalAI/blob/d4fb7bfda7a2da5480e1187e8d3e40884b42ba11/applications/Chat/coati/kernels/opt_attn.py#L72) You use attn_bias which is not found in the 0.0.12 xformers ``` attn_output...