Hong Li

Missing variable is:CMAKE_CUDA_DEVICE_LINK_EXECUTABLE

2

**Describe the bug** I follow“ https://colmap.github.io/install.html ”Instructions to install colmap . However, an error occurred when I executed "cmake .." like this image:  The bug situation is shown in...

## I encountered some problems in the process of environment configuration. The solutions are as follows: #### 1. BFM cd examples/Data/BFM and View "readme.md", download files and create the corresponding...

Thank you for your work，I want to test methods based on BFM model, such as 3ddfa, deepfacecon or synergynet; What is the index correspondence of landmarks? Should I set the...

I have got the coordinates of the model in the pixel plane. How can I use pytorch3d for raster rendering without setting the camera?

1

## ❓ Questions on how to use PyTorch3D NOTE: Please look at the existing list of Issues tagged with the label ['question`](https://github.com/facebookresearch/pytorch3d/issues?q=label%3Aquestion) or ['how-to`](https://github.com/facebookresearch/pytorch3d/issues?q=label%3A%22how+to%22). **Only open a new issue if...

cmake error:"build" does not exist?

4

CMake Error: The source directory "/home/lh/code/3.Nerf/instant-ngp/build" does not exist. After I cloned instan ngp, the build folder was not found？ 

When I execute the third line of code in the "hello world" program, the following error occurs.

3

Blender 3.3.1 (hash b292cfe5a936 built 2022-10-05 00:14:35) /run/user/1000/gvfs/ non-existent directory [00:04:03.622] [root] [INFO] | Converted args.seed='0' to scene_seed=0, parsed as hexadecimal [00:04:03.640] [root] [INFO] | infinigen version 1.0.0 [00:04:03.640] [root]...

RuntimeError: Error(s) in loading state_dict for Resampler:

5

I encountered this problem while loading the face_adapter.： RuntimeError: Error(s) in loading state_dict for Resampler: size mismatch for proj_out.weight: copying a param with shape torch.Size([2048, 1280]) from checkpoint, the shape...

multiple GPUs is slower than running on a single GPU

4

### System Info ```Shell - `Accelerate` version: 0.25.0 - Platform: Linux-5.4.0-135-generic-x86_64-with-glibc2.31 - Python version: 3.10.13 - Numpy version: 1.26.3 - PyTorch version (GPU?): 2.1.1+cu118 (True) - PyTorch XPU available: False...

Why use VAE or VQ-GAN/VAE， not AE？

4

Why does the Latent Diffusion Model use **variational autoencoders (VAE)** or similar generative models like **VQ-GAN/VAE** for compression instead of using **AutoEncoder (AE)?** If AE can be considered a one-to-one...