Comments (5)
Maybe you didn't get the right cropping so the scene is moving? I'm not sure. Or the dataset transfer requires more training. I didn't try VoxCeleb2, but my continue training on VoxCeleb1 is ok. You can check the reconstruction samples after each epoch to see whether such problem exists, or whether there are ridiculous keypoints residing far from the face.
Actually I didn't use training tricks. Maybe the only thing needed is to increase the learning rate if you have large batch.
from face-vid2vid.
Thank u a lot! I have solved the problem, it's the problem of the datasets.
And now I have another question about the training process. Now I'm training on vox2 from the scratch, has been two days about 10 epochs, but the vis results demonstrate there is no difference between source and prediction.
Considering the cost of training(time and money), I want to know whether my training params is wrong, or training time is not enough. Could you share with me, you can see some difference between source and predictions after how many epochs?
Thank you.
from face-vid2vid.
When the headpose loss (H in log) decreases from 200+ to 50, the prediction pose starts to align with driving. On Vox1 10 epochs is enough (for num_repeates=100), but Vox2 may take more. At first the reconstruction demonstrates much distortion, as the training goes on, the distortion is weaker and the expressions start to align with driving, too.
from face-vid2vid.
您好!想问一下设置num_repeates=100和将num_repeates设置成1然后epoch设置*100倍有区别吗?不是很清楚为什么一个epoch下还要设置多个num_repeates
from face-vid2vid.
没有区别。因为默认开启id sampling,会对identity均匀采样,vox1共1152个id,也就是一个repeat只有1152组样本,通过增加repeat来减少epoch数。
from face-vid2vid.
Related Issues (11)
- Will you please share the trained checkpoint ? HOT 4
- load_videos.py - Can not load video UW1c9E8nfxQ, broken link HOT 3
- 这块的sota还是这个吗 HOT 2
- about the ckp epoch HOT 2
- 你好,请问你可以分享一下处理好的数据集吗 HOT 20
- about the nework HOT 3
- There is a problem with the generated video, what is the cause? HOT 9
- Keypoint prior loss function HOT 2
- What is the version number of imageio? Thank you very much~ HOT 7
- training data and command HOT 2
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 face-vid2vid.