Comments (7)
Hi @hzh8311, The two numbers are used to aproximatevly map the center and the scale obtained from a tight bounding box to the one used during training.
Regarding the results: You should get around 74% if you run this code. For LS3D-W balanced you have to remove the 1.75 shift at this line:
2D-and-3D-face-alignment/main.lua
Line 116 in fc4d299
from 2d-and-3d-face-alignment.
So why 1.75 here? Should not it be 1. ?
from 2d-and-3d-face-alignment.
It seems that the center
and scale
for training are fixed as (225, 275) and 1.8, respectively. And the center
and scale
for testing are computed according to bounding box. Does this difference matters and leads to such performance drop (17-18%)? @1adrianb
from 2d-and-3d-face-alignment.
@hzh8311 the center is fixed for 300W-LP because the images are already normalised and therefore computing a bounding box is not required. At test time however the faces are coming in all sort of sizes and are found at various locations in the image, therefore some sort of normalisation is required. This is done for simplicity based on the bounding box size.
The error of 17% is not coming from normalisation diff, but from the shift between the ground truth and the predictions. The shift is applied after the predictions are obtained.
from 2d-and-3d-face-alignment.
I removed the shift you mentioned, but only 3-4% improvement compared to my first result. That is to say it is still 13-14% lower than the result reported in the paper.
For more details, the AUCs on traning set and validation set(300W_LP_test) are quiet high (~80%), but it drop badly on LS3D-W dataset.
from 2d-and-3d-face-alignment.
Oh, so you are using a retrained model? Because using the pretained model, already provided, you should be able to match exactly that numbers.
from 2d-and-3d-face-alignment.
Yes, but I can't figure out why the retrained model can not reach your performance.
from 2d-and-3d-face-alignment.
Related Issues (20)
- Install fb-python on windows? HOT 2
- LS3D-W Checksum HOT 1
- About .mat file HOT 1
- Bad result!! HOT 1
- Converting .t7 labels into other formats HOT 3
- Can not run this demo on CPU HOT 1
- Regarding licence of model file and dataset. HOT 4
- Hair of the 2d face
- Can not download the pre-trained models HOT 1
- About the LS3D-W annotation HOT 5
- Scale factor in utils transform and get_normalisation HOT 1
- Cannot achieve same result in paper HOT 4
- Groundtruth bounding box for training HOT 1
- 2D-3D landmarks output . how? HOT 3
- Hi,In your paper, the AFLW is splited to 3 parts, how to split it? It seems the AFLW2000 dataset I downloaded is a whole folder. HOT 2
- Support for MacOS HOT 1
- 3D Alignment HOT 1
- Query regarding dataset annotation HOT 1
- why the heatmaps are of size 64x64 while images are of size 256x256 HOT 1
- Mapping from LS3D-W balanced to the LS3D-W images 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 2d-and-3d-face-alignment.