ustbzgn comments

Results 9 comments of


                                            ustbzgn

When you publish the config and model of PTv3 trained on SematicKITTI

Ok, got it. Thanks for your time, I am looking forward to your per-trained models. Wish your new project success.

could you provide the rendering scripts to evalutate ?

@Costwen 你好啊佬，想请教以下怎么渲染图像的，我渲染的RGB图总是有些小问题，希望能交流一下

could you provide the rendering scripts to evalutate ?

@Costwen 我们愿意给你一定的报酬，作为交换

could you provide the rendering scripts to evalutate ?

> > @Costwen 我们愿意给你一定的报酬，作为交换 > > Syncdreamer的脚本改一下setting就行https://github.com/liuyuan-pal/SyncDreamer/tree/main?tab=readme-ov-file 非常感谢指引，请问你有深度图和法线图渲染方法吗

could you provide the rendering scripts to evalutate ?

> > @Costwen 我们愿意给你一定的报酬，作为交换 > > Syncdreamer的脚本改一下setting就行https://github.com/liuyuan-pal/SyncDreamer/tree/main?tab=readme-ov-file 佬，Syncdreamer渲染脚本里边没有设置相机FoV参数的，这个你有考虑吗

Train on nerf of stage 1 with custom dataset

> > I'm sorry I have no idea on this problem. > > Thanks ， can you share a training sample, I think there is something wrong with my render...

Training CUDA Out Of Memory error

@fffh1 Hello, did you solve it? I meet the same problem

Training CUDA Out Of Memory error

关于RUN_CUDA_RWKV6这部分，最好用pytorch实现，否则不方便移植

联名上书，希望官方大佬复现Pytorch版本，https://github.com/TorchRWKV/rwkv-kit这个仓库复现的需要加载预训练模型的权重，希望官方复现一个能从头训练的pytorch版本，这样才能有正真和transformer对抗的基础生态