Comments (5)
While we identify and resolve the issue, you can also use the CPU mode with the —force_cpu flag.
Use this command:
python app.py —force_cpu
from refacer.
Video size: 640x352
src image size: 512x583
dst image size: 512x512
TENSORRT mode with providers ['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider']
from refacer.
With CUDAExecutionProvider it works!
from refacer.
Thank you for reporting this issue. In order to better diagnose the problem, could you please provide more information? Specifically, could you share the size of the video you're trying to process and the size of the images you've uploaded as faces?Also, could you please specify which ProcessExecutor the program is picking up? Is it TensorrtExecutionProvider or CUDAExecutionProvider?
I apologize for the inconvenience, I'm aware that the error handling and messaging need improvements. Your feedback is extremely valuable in this regard.
I want to add that initially, my focus was on functionality. I have recently been working on performance enhancements. Now, I'm about to shift my focus to better error handling. While I work on identifying and resolving this issue, I would suggest trying out the application on Google Colab, if possible. This might offer a temporary workaround. Thank you for your understanding and patience.
from refacer.
While we have not yet resolved the bug, we have disabled TensorrtExecutionProvider. It should now automatically use CUDAExecutionProvider and should work for you. Could you let us know if this is the case? At the moment we don't have an NVIDIA GPU to test on
from refacer.
Related Issues (20)
- refacer and roop parralel installation causes problems. HOT 12
- refacer web-interface uses same port as automatic1111 aka stable diffusion. HOT 1
- How can I increase the number of faces? HOT 1
- Error
- Doesn't recognise face from photo so doesnt swap. HOT 1
- Unable to determine which face was not detected
- The localhost doesn't work normally. HOT 5
- Error and doesn't work HOT 2
- Crashing at extracting frames. HOT 1
- (question for a friend) press reface but nothing appears in terminal HOT 2
- "CUDAExecutioner" In terminal missing after I accidentally uninstalled onnxruntime HOT 1
- Add option to use codeformer? HOT 1
- Option to swap to all faces? HOT 2
- I don't know what caused it, please help determine.
- Limitation Of a Video File? HOT 2
- numpy.core._exceptions._ArrayMemoryError
- Insightface Issue
- Hello, dnt work on colab HOT 2
- Issue HOT 2
- Error when creating a video
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 refacer.