Comments (17)
You are right, the loss is always small as VOCA regresses vertex offsets. Rather than on the printed loss I recommend checking the Tensorboard graphs which show the progress better
from voca.
You are right, the loss is always small as VOCA regresses vertex offsets. Rather than on the printed loss I recommend checking the Tensorboard graphs which show the progress better
And I try to regress the blend shape coefficient directly, but it doesn't converge
from voca.
What are you referring to as blend shape paramters? FLAME jaw pose and expression parameters?
How did you obtain these parameters?
from voca.
By the 3DMM method,only compute the expression parameters.
from voca.
What is the 3DMM method? Can you please be a bit more specific?
If you use FLAME, the expression parameters are insufficient, as opening the mouth is modeled as jaw rotation. In this case you would need to regress the three parameters for jaw AND the expression parameters.
from voca.
https://cseweb.ucsd.edu/~ravir/6998/papers/p187-blanz.pdf
from voca.
I am well aware of this paper, the model however for this is not publicly available.
So what model did you use and how did you compute the model parameters?
from voca.
The parameters of face identity and expression parameters are obtained by 3dmm face reconstruction, and then the expression parameters are used as ground truth value of voca to train.
from voca.
So you fitted the model to images to get identity and expression parameters (supposedly of Basel Face model)? Is that what you did?
What data did you use to fit the model to?
from voca.
yes,i do. Some videos downloaded from the internet.
from voca.
These videos are mainly some speech videos of the host. And network removing the output_decoder module,regress the expression coeffs directly.
from voca.
It is quite difficult to judge what is the problem as you are using 1) different data which are not comparable to the quality of the VOCA training data, 2) a different statistical model and 3) a different loss as you are regressing model parameters rather than vertex offsets. For this you must have changed the provided architecture.
If you want to experiment with regressing model parameters, I would recommend starting with parameters for the VOCA training data. Given that the data are provided in FLAME topology, it is easy to compute model parameters for these data. In this case you can at least rely on the amount and quality of the training data.
from voca.
Yes, I have made some changes to the code based on the voca structure, mainly the input and output parts.
Later, I will try a direct regression expression coefficient experiment based on the voca training set.
Thank you very much for your reply. Hope to communicate with you latter.
from voca.
Having the right size and quality of the training data is quite essential for training. Good luck with your further experiments.
from voca.
I quite agree with you. Thanks.
from voca.
In the training set, the loss is small, but in the verification set, the loss is relatively large. Do you have any suggestions to solve the fitting problem?
I found a phenomenon that in the beginning of some iterations, the loss on the verification set is decreasing, and the more training iterations, the loss will even increase. Is it over fitting due to overtraining?
from voca.
@youngstu Hi, I have the same problem as you, regressing bs coefficients but not converging, similarly, the verification loss is large, did you solve this problem?Thanks.
from voca.
Related Issues (20)
- Should --uv_template_fname be the same as --template_fname in run_voca.py?
- can you give pretrained_models?
- Initialization Of Decoder Layer
- Problem of training voca
- How to control expression in the edit_sequence.py? HOT 2
- Can I train this on custom dataset?
- Unknown mesh file format. HOT 1
- Training with new Tensorflow Version
- Unsolved reference tfbody
- Missing data on subj_seq_to_idx.pkl file HOT 1
- If I want to control the expression of the eyes, how should I set the parameters?
- I haven't found the 'output_graph.pb' file, where can I get it?
- dataset/voca_face_former/templates.pkl not found HOT 1
- Where to download npy and pkl files HOT 1
- Inference other .ply files
- Hot to get blink_exp_betas for another flame version?
- Is the the vertice's coordinates in registered data the same as it in data_verts.npy in training data? HOT 1
- How extract FLAME parameters (expression, jaw) from vertex offset. HOT 1
- After add eyeblink, the face twitches HOT 2
- Exporting/importing meta graphs is not supported when eager execution is enabled. No graph exists when eager execution is enabled.
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 voca.