Xiaoran JIAO comments

Results 4 comments of


                                            Xiaoran JIAO

ConvNeXt poor results

> We will update the configuration, which can be used to reproduce the classification result #1256 Hi! Could you please tell me what effect does the original ConvNeXt implementation have...

RuntimeError: tinycudann/bindings.cpp:81 check failed params.device().is_cuda()

I also encountered the same issue, and I'm certain that I'm using the default configuration file.

hello，both zero123 and syncdreamer use views of 256 resolution for training, can we scale it to 512 without OOM?

Hi @liuyuan-pal, thanks for your wonderful work! I wanted to express my appreciation and inquire if there are any plans to release your training data on platforms such as OpenDataLab,...

hello，both zero123 and syncdreamer use views of 256 resolution for training, can we scale it to 512 without OOM?

> Hi, I've tried OpenDataLab, but it seems I cannot create a new dataset. > > > Hi @liuyuan-pal, thanks for your wonderful work! I wanted to express my appreciation...