Comments (7)
- reconstruction loss should be around 1e-3~1e-4 for a well-trained model. You can see the reconstructed example in my colab example which is presently added.
- No. I can't share the loss graph.
- Yes. I didn't clip the gradient. The grad_clip option to zero means no clip.
from faceshifter.
Hi! Thanks for your compliments.
Training with only CelebA-HQ is quite a dangerous choice.
The dataset bias can be affected to total loss.
In your loss graph, reconstruction loss is very high.
Maybe you should try to increase the coefficient of reconstruction loss if you wanna train with only CelebA-HQ.
Be careful about overfitting.
from faceshifter.
Hi! Thanks for your compliments.
Training with only CelebA-HQ is quite a dangerous choice.
The dataset bias can be affected to total loss.
In your loss graph, reconstruction loss is very high.
Maybe you should try to increase the coefficient of reconstruction loss if you wanna train with only CelebA-HQ.Be careful about overfitting.
Thank you so much for your reply!
By the way, what is the expected value of reconstruction loss of your well-trained model? If possible, could you share your loss graph as a reference? Did you set grad_clip to zero?
from faceshifter.
Could you please tell me how long does it take to finish the training?
from faceshifter.
Could you please tell me how long does it take to finish the training?
For celebHQ dataset only, it takes 2-3 hours for an epoch.
from faceshifter.
Could you please tell me how long does it take to finish the training?
For celebHQ dataset only, it takes 2-3 hours for an epoch.
can you benefit from multi-GPU training? does it really increase the training speed?
from faceshifter.
已经过去四年了,请问下你能分享下arcface.pth文件吗,链接已经失效了,感激不尽
from faceshifter.
Related Issues (20)
- how many images are necessary to have good results? HOT 1
- Which dataset do you use to train your own arcface? HOT 1
- GPU Memory HOT 2
- Coefficients of loss HOT 3
- some error with aei_inference.py HOT 3
- multi GPU training HOT 1
- Colab Example-FaceShifter.pth HOT 4
- Should affine be set as False in your ADD layers? HOT 1
- The implementation of ID Loss seems different from the original paper HOT 2
- Have you ever encountered this phenomenon: attr loss down to near 0 and rec loss keeps at 0.01 and doesn't got down? HOT 2
- A question about train step HOT 1
- TypeError: __init__() got an unexpected keyword argument 'early_step_callback' HOT 1
- Can anyone share a pretrained model?
- Can you provide the pre-trained arcface.pth? HOT 2
- The link of pre-trained Arcface model is expired
- DeepFace HOT 1
- identity encoder code not found HOT 7
- where is val set
- CUDA out of memory. HOT 4
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 faceshifter.