Comments (7)
I found that this training can be run normally without using LeakyReLU, and I believe it is caused by inconsistent data shapes during computation loss caused by LeakyReLU
from wav2lip_288x288.
Have you verified the author before uploading the code @primepake
from wav2lip_288x288.
It's due to PReLU, PReLU could have negative output to audio vector and face vector, and the cosine_similarity will have negative value.
@primepake Could you share your method to solve this problem?
I saw you mentioned that using BCELogicLoss would have other problem, I think the training loss will stay near 0.6...
Did you still use cosine_loss in color_syncnet_train.py or change to other loss function?
Thanks in advance!
from wav2lip_288x288.
For the same question, the author mentioned the use of BCELogicLoss, but in the subsequent answer, he suggested not to use it. If you do not use BCELogicLoss, you will not be able to train. So what is the correct way to deal with it? @primepake
from wav2lip_288x288.
I recommend you shouldn't you BCELogicLoss, this not correct. You should apply ReLU in the last layer to get the value in range [0,1]
from wav2lip_288x288.
I recommend you shouldn't you BCELogicLoss, this not correct. You should apply ReLU in the last layer to get the value in range [0,1]
Thank you very much, it worked
from wav2lip_288x288.
I recommend you shouldn't you BCELogicLoss, this not correct. You should apply ReLU in the last layer to get the value in range [0,1]
Thank you very much, it worked
Could you share your method to solve this problem?
from wav2lip_288x288.
Related Issues (20)
- the input of lpips loss HOT 1
- High resolution dataset HOT 1
- Hi sir, I am a beginner and I would like to inquire whether I should prepare a video of no less than 288 or a video of 384
- Find friends who are training models and share ideas with them.Welcome HOT 3
- Train syncnet use SyncNet_color_384 but train wav2lip use SyncNet_color? HOT 1
- When I use hq_wav2lip_sam_train.py。 HOT 3
- DINet implementation HOT 1
- video clips length
- train_syncnet_sam.py is not using GPU (RTX 4090) HOT 1
- What indicator represents the end of training hq_wav2lip_sam_train? HOT 4
- Why my train loss after introducing sync loss? HOT 4
- How to train HOT 6
- Why can’t training start? HOT 1
- do inference
- Generated bottom half face always blur. HOT 2
- Training failed. The lip shape of a character cannot change according to changes in speech HOT 6
- Syncnet loss does not converge HOT 20
- dataset
- DINet HOT 1
- 这个和普通的easyw字幕交换网站lip有什么区别
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 wav2lip_288x288.