Hong Li

> Sounds like an issue where `CUDA` wasn't enabled as a language in the root CMakeLists.txt，Refer to the [https://cliutils.gitlab.io/modern-cmake/chapters/packages/CUDA.html，you](https://cliutils.gitlab.io/modern-cmake/chapters/packages/CUDA.html%EF%BC%8Cyou) can add > > ``` > if(NOT DEFINED CMAKE_CUDA_STANDARD) > set(CMAKE_CXX_STANDARD...

Hello, I am also trying to reproduce the results of the paper. I was wondering if you have downloaded the complete data file views_release.tar.gz and how much storage space it...

> 请问一下，潜在扩散模型到底是用VAE，还是用了VQ-GAN，实际情况下，哪一个更有优势呢？ ldm 的 readme 中展示的实验结果是 vae 可以用更少的 steps 达到更低的 FID

you can refer fomm：https://github.com/AliaksandrSiarohin/first-order-model/tree/master/sync_batchnorm

I solved this problem. The cmake version is too low

I'm trying to use the function “unwrap_vertex_to_uv” to unwrap the **spatial position coordinates** of the vertices to UV, but I'm encountering issues **with bilinear interpolation and resampling based on the...

my code and results： def visualize_3dmmver_as_uv(self): ver_vertex = self.pred_vertex[0, :, :].detach().cpu().numpy() unwrap_uv_idx_v_idx = self.facemodel.unwrap_uv_idx_v_idx.detach().cpu().numpy() unwrap_uv_idx_bw = self.facemodel.unwrap_uv_idx_bw.detach().cpu().numpy() vertex_uv = unwrap_vertex_to_uv(ver_vertex, unwrap_uv_idx_v_idx, unwrap_uv_idx_bw) return vertex_uv def inverse_vertex_from_vertex_uv(self, vertex_uv): vtx_vt = (self.facemodel.vtx_vt...

搭建不了，可以先用低版本机器处理好数据；算法运行方面可以使用高版本cuda

I have a similar doubt. It seems that the author does not directly use the sampling process provided by DDPM in the code.  Instead, the mean of $x_{t-1}$ is...

You can refer to https://zhuanlan.zhihu.com/p/569994589 for a detailed derivation of DDPM, and the same applies to DDIM.