Comments (4)
Thanks for sharing. Brilliant work!
I notice thatbatchsize
is set to 1 as mentioned in your paper. Is it by design or just some concession to hardware limitation?Thank you
I found the face will be smoothed if batchsize too big. But I'm not sure if is related to batchsize. I changed batchsize to 1 and still training now.
from gpen.
Just some concession to the hardware limitation.
from gpen.
Thanks for sharing. Brilliant work!
I notice thatbatchsize
is set to 1 as mentioned in your paper. Is it by design or just some concession to hardware limitation?Thank youI found the face will be smoothed if batchsize too big. But I'm not sure if is related to batchsize. I changed batchsize to 1 and still training now.
Do you have more info about batch size now?
from gpen.
Thanks for sharing. Brilliant work!
I notice thatbatchsize
is set to 1 as mentioned in your paper. Is it by design or just some concession to hardware limitation?Thank youI found the face will be smoothed if batchsize too big. But I'm not sure if is related to batchsize. I changed batchsize to 1 and still training now.
Do you have more info about batch size now?
A simplified version of the training code will be released soon. Stay tuned.
from gpen.
Related Issues (20)
- Can it work on RGBA images?
- Have you tried with your FullGenerator_SR model?
- Confusing in the umeyama implementation. HOT 1
- Can't manage to find a download link for GPEN-BFR-2048 model. HOT 2
- about automatically rotated
- About the input resolution of "net_d.pt"
- TensorRT deployment HOT 3
- 部分人脸会出现磨皮很严重和人脸凭空出现黑痣的现象,有解决思路吗 HOT 1
- Unclear step (run codes) HOT 2
- 你好,发布一个可微调的GPEN-BFR-512模型吗?
- FullGenerator_SR
- eval lpips HOT 4
- Training results are normal, but test results abnormality HOT 1
- from face_detect.retinaface_detection import RetinaFaceDetection ModuleNotFoundError: No module named 'face_detect'
- why no weight_decay and scheduler for train_simple.py?
- How to convert FullGenerator to ONNX
- GPEN-BFR-2048 in ONNX format
- Adversarial Loss without any change at 0.69
- Do I need to load the discriminator when fine-tuning the model?
- Cannot install modelscope HOT 1
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 gpen.