Comments (15)
I had the same error on a remote instance of Google Colab, and instead of using EGL I installed OSMesa per https://pyrender.readthedocs.io/en/latest/install/index.html#installmesa
I then set the environment variables inside the visualize_sequence.py
and rendering.py
This also fixed the textured version and I noticed no frame drops with the same renders from @a35026
from voca.
I found one solution, downgrading your openGL version by using:
pip install pyopengl==3.1.0
When I using the above 3.1.0 pyopengl version, I got everything works well.
from voca.
Great, thank you. If you find any good solution, I would be happy to adapt the repository to resolve this rendering issue
from voca.
Hi @Augnine did you find a solution?
I was working on voca and same issue came when I ran python run_voca.py and only audio is saved in the animation output folder and meshes are stored seperately in meshes folder
I would like to know what am I doing wrong here
from voca.
@TimoBolkart I have same issue. How to deal with? Thanks.
from voca.
Thank you for your interest in VOCA @Augnine @Passionatecricketer and @Adorablepet, the problem seems to be with the actual rendering rather than the VOCA mesh generation. There had been several attempts to overcome the rendering problems, maybe check this issue for some possible solutions. Please provide some feedback if any of these things work for you.
An alternative is to use another rendering framework. I am happy to support replacing pyrender by something more reliable if there are any good suggestions
from voca.
Hi @TimoBolkart I tried the solutions provided in the issue that you mentioned. But none of them seem to work as I am currently working on debian and there are some issues with regards to making build of osmesa. I'll update once I get a workaround. Meanwhile if someone has any another solution please let me know.
Thanks for the reply @TimoBolkart !
from voca.
One option could be to just replace pyrender with some other rendering framework like Tensorflow Graphics or DIRT or any other renderer. I have not looked into those so I don't know what are their pitfalls and how difficult they are to integrate.
from voca.
Ok. Thanks for the idea. I'll try it and update the thread if something works out
from voca.
Adding following lines to the rendering.py seems to solve the problem for some people:
import os
os.environ['PYOPENGL_PLATFORM'] = 'egl' # Uncommnet this line while running remotely
I updated the script accordingly
from voca.
Getting this output with the latest default configuration: https://imgur.com/a/alRE8Zm
Texturized animation showed same warnings but generated just black frames from np.zeroes
Interesting that it worked only when I had added the same snippet os.environ['PYOPENGL_PLATFORM'] = 'egl'
to visualize_sequence.py
not just to rendering.py
But there also were 3 dropped frames, you can notice them here:
https://imgur.com/a/pAnek7R
Ubuntu 16.04, CUDA 10.2, Nvidia: 440.59, python 3.6.11, pyrender 0.1.43, trimesh 3.8.8
@TimoBolkart could you please share pyrender and trimesh versions you use for animation?
from voca.
Getting this output with the latest default configuration: https://imgur.com/a/alRE8Zm
Texturized animation showed same warnings but generated just black frames from np.zeroes
Interesting that it worked only when I had added the same snippetos.environ['PYOPENGL_PLATFORM'] = 'egl'
tovisualize_sequence.py
not just torendering.py
But there also were 3 dropped frames, you can notice them here:
https://imgur.com/a/pAnek7RUbuntu 16.04, CUDA 10.2, Nvidia: 440.59, python 3.6.11, pyrender 0.1.43, trimesh 3.8.8
@TimoBolkart could you please share pyrender and trimesh versions you use for animation?
Hi, @a35026 I've seen your generated video. Would you please tell me how you're able to produce the video with a real face and not with the default 3d avatar of voca?
from voca.
Thank you so much.. @hammad93
from voca.
I found one solution, downgrading your openGL version by using:
pip install pyopengl==3.1.0
When I using the above 3.1.0 pyopengl version, I got everything works well.
why I run “run_voca” still report errors “pyrender: Failed rendering frame”?I have try many solution in "issue" but still haven't solve it.
from voca.
Quite the opposite, I solved the problem by just commenting out the os.environ['PYOPENGL_PLATFORM']='egl'
in rendering.py
.
from voca.
Related Issues (20)
- Windows support and installing MPI-IS / mesh HOT 1
- Should --uv_template_fname be the same as --template_fname in run_voca.py?
- can you give pretrained_models?
- Initialization Of Decoder Layer
- Problem of training voca
- How to control expression in the edit_sequence.py? HOT 2
- Can I train this on custom dataset?
- Unknown mesh file format. HOT 1
- Training with new Tensorflow Version
- Unsolved reference tfbody
- Missing data on subj_seq_to_idx.pkl file HOT 1
- If I want to control the expression of the eyes, how should I set the parameters?
- I haven't found the 'output_graph.pb' file, where can I get it?
- dataset/voca_face_former/templates.pkl not found HOT 1
- Where to download npy and pkl files HOT 1
- Inference other .ply files
- Hot to get blink_exp_betas for another flame version?
- Is the the vertice's coordinates in registered data the same as it in data_verts.npy in training data?
- How extract FLAME parameters (expression, jaw) from vertex offset.
- After add eyeblink, the face twitches
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from voca.