Comments (7)
You are right, that should be reshape(30, 7*7)
. I actually forgot to test the inference=True
version, because tracker.py
is currently doing the manual landmark decoding. Actually, I think I forgot to consider the batch size as well, even though I'm pretty sure I had it working correctly for the bigger models. I'll check what's going on there.
As a side note, the points for the 30 point model are laid out like this.
from openseeface.
model.py
should be fixed now in cfe2e2f. The models should work with bigger batch sizes and inference=True
as well. The random output was most likely related to the different factor applied to the sigmoid to work better with the lower resolution. I've attached the output of the new model on one of the WIDER FACE images.
from openseeface.
Thanks, the issue is fixed.
Before closing this, I'd like to ask if you still have the trained ShuffleNet-V2 PyTorch weights to share? Thanks.
from openseeface.
I think I can find those, but they were trained on a less refined dataset and with less augmentation, so they're not really comparable. Are you still interested?
from openseeface.
Yes that would be great if you could find them. I'm planning to retrain it, that'd be good to start from a pretrained model. Many thanks.
from openseeface.
I think it should be these.
from openseeface.
Thanks a lot. closing this issue.
from openseeface.
Related Issues (20)
- not support macbook HOT 5
- About generating landmark heatmap offset groud truth label HOT 3
- onnxruntime-gpu (CUDA/TensorRT) support HOT 1
- [FR] VMC support HOT 10
- Unable to fulfill dependencies HOT 13
- Packets on 369 of facetracker.py fail with VPN enabled HOT 2
- [SUGGESTION] officially support OpenSeeFace as a flatpak HOT 8
- Using the project for API HOT 2
- [Compatibility request] Unity Barracuda ML solution support for the .onnx models in project HOT 6
- Extracting face with quaternion points HOT 3
- error in converting onnx models to tensorflow HOT 5
- Worse performance of released pytorch models HOT 1
- NumPy 1.24 breaks pupil/gaze tracking HOT 2
- Detection model without onnxruntime HOT 2
- Documenting UDP protocol HOT 1
- [Question] Camera opened by dshowcapture has changed? HOT 1
- model loading error HOT 5
- randomly black out when ir tracking (lenovo 500) HOT 2
- Openseeface runs but vseeface cannot communicate with it. HOT 1
- The Lazy Eye 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 openseeface.