Comments (4)
Hi,
I think it impossible to fully utilize the gpu without some kind of batch processing, because there is not much gpu computation per one frame.
About slow processing speed - currently it writes every output frame to the disk - i believe it's the main bottleneck of the pipeline. I'm planning to do frame saving optional and write output directly to a video file (avoiding long access to the disk).
from simswap-inference-pytorch.
Looking forward to the direct video file output feature, thanks for the answer
from simswap-inference-pytorch.
Hi, I think it impossible to fully utilize the gpu without some kind of batch processing, because there is not much gpu computation per one frame.
About slow processing speed - currently it writes every output frame to the disk - i believe it's the main bottleneck of the pipeline. I'm planning to do frame saving optional and write output directly to a video file (avoiding long access to the disk).
Loving this update its really made night and day difference
Any update on that @mike9251 ?
from simswap-inference-pytorch.
Also i got this response, i think i followed all the steps before so no way for me to double check it again, but does this path from start to finish change anything ? he is getting much better results than i am : https://github.com/neuralchen/SimSwap/issues/352#issuecomment-1364002526
from simswap-inference-pytorch.
Related Issues (20)
- cloud gpu HOT 1
- OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized. HOT 1
- ашду onnxruntime_pybind11_state.pyd addresses the certain local files:
- GPU not used in windows 11 HOT 1
- Error executing job with overrides: HOT 4
- I'm having a problem with overlapping faces. HOT 3
- I haven't been able to match the faces in the Multispecific folder. HOT 1
- GFPGAN Model and multispecific HOT 2
- For improve gpu utilization HOT 1
- Torch not compiled with CUDA enabled HOT 2
- Anyway to remove 'Deepfake' watermark? HOT 7
- Feature: GIF support
- Help HOT 4
- Only cpu! HOT 3
- How to do a batch inference?
- 如何提高推理速度?我尝试加入多线程但是不生效
- Always error when video finishing compile image, Hydra. HOT 1
- pipeline devices
- Error trying 512 simswap. loading state_dict
- does it work with the latest simswap training model ?
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 simswap-inference-pytorch.