Comments (4)
Hi @kuhnkeF,
Yes, it was intended and it was done in order to bring it at close as possible to the lua torch version (see: https://github.com/1adrianb/2D-and-3D-face-alignment/blob/fc4d29999a1f0b8a833805bfe437bd32df886242/utils.lua#L187 )
This value is however dependent on the face detector used, so it can probabably further be tweaked.
You should however notice an increase in the accuracy after the last update. If this is not the case, please let me know.
from face-alignment.
Thank you.
I don't have any real comparison for the accuracy, but it seems to be better.
What are the best settings that I should use if the bounding boxes are created from ground truth/manually labeled landmarks?
from face-alignment.
The existing values are already picked with the assumption that the bounding box is close to a tight bounding box (a ground truth one). I did play with values in the 190-220 range at some point but I didn't notice a major difference.
from face-alignment.
great! Thanks again.
from face-alignment.
Related Issues (20)
- about tensor input HOT 1
- Error in examples/demo.ipynb testing on a batch
- get_landmarks_from_batch returns an empty list
- Incorrect Landmark HOT 1
- Tiny and Smaller pretrained models!
- I can't use it by GPU HOT 1
- fail to get 2d landmark in float dtype
- Change path to pretrained models
- [update pypi] Update the apple silicon support version HOT 1
- Retroactive change in version 1.3.5 package
- How to filter the abnormal face?
- Is there any way to parallelize the post-processing code in `batch_detect`? HOT 1
- onnx version of this model
- Detect eye blink?
- new pip pag refer
- Is there any way to locate the obscured landmarks? HOT 1
- Are the face alignement landmark result same as dlib?
- RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory HOT 1
- When i use face_alignment.FaceAlignment(face_alignment.LandmarksType.THREE_D, flip_input=False), Why the key point shape of the last picture is (1, 1, 68, 3), and the shape of other images are (1, 1, 68, 2)
- Why I just can't run the test case you provided? 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 face-alignment.