search

GDAOSU / vis2mesh

Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility ICCV2021
97 stars 16 forks source link

python inference.py example/example1.ply --cam cam0 #5

Open shangfenghuang opened 2 years ago

shangfenghuang commented 2 years ago

Load Cam Info: Peek First Cam:

K: 150 0 128 0 150 128 0 0 1 R: 0.998805 0.0209822 -0.044135 -0.0162957 -0.708441 -0.705582 -0.0460717 0.705458 -0.707253 C: -2.0875 -32.9513 -7.10067 w 256 h 256 Load cloud (+v 1999961) Load mesh (+v 0) (+f 0) Segmentation fault (core dumped)

sxsong1207 commented 2 years ago

Hi JMU-HSF, could you provide more details about the issue? Your os, running environment (docker or build from source), etc.

shangfenghuang commented 2 years ago

image the docker enviroment is according the readme. I'm not change it. when I run the inference.py, the could show the "FileNotFoundError: [Errno 2] No such file or directory: '/workspace/example/example1.ply_WORK/VDVNet_cam0/render/pt0.flt". torch 1.9.0 CUDA is avaiable:True, version is 10.2 , python 3.7.0. I create the docker environment according the provided Docker file and enter docker according the endocker. sh file.

sxsong1207 commented 2 years ago

Hi JMU-HSF,

Thanks for your interest in our project and sorry for the late reply. I just take a look from my side. The program in docker is somehow strange behavior, a lot of ##.so not found warnings and this segmentation fault. Sorry, I am not an expert in Docker I cannot make it perfect at this stage.

I tried the same way to call the render_seg.json in Docker: image

The segmentation fault error is not very informative, but I guess, your docker environment doesn't support graphic cards, since the rendering requires OpenGL ES (EGL), which requires the nvidia-container. Have you installed this package in your system?

sudo apt-get update && sudo apt-get install -y nvidia-container-toolkit