Comments (4)
Maybe something goes wrong for my last test!
I re-ran again and get the right result as bellow,
We can conclude:
- 1-gpu training script provided by your readme can reproduce the accuracy of paper
- https://github.com/wondervictor/WiderFace-Evaluation is about 2~4% lower than that of offical
eval tools
from img2pose.
Hello,
The eval tools are just Matlab scripts provided with the WIDER FACE dataset.
It is the official scripts to get mAP and plot curves on WIDER FACE.
You can find a short description on how to use it in #8.
Although I haven't tested, you can also try non official python code from any GitHub repo. One example can be found at https://github.com/wondervictor/WiderFace-Evaluation
Hope this helps.
from img2pose.
@vitoralbiero
As the paper reported, the AP@val is
Easy Val AP: 0.908
Medium Val AP: 0.899
Hard Val AP: 0.847
However, the result of scripts in https://github.com/wondervictor/WiderFace-Evaluation is much lower than the former one.
Easy Val AP: 0.8469243842505618
Medium Val AP: 0.827844108399036
Hard Val AP: 0.7493400384483289
I use the model mentioned in your readme
python3 evaluation/evaluate_wider.py \
--dataset_path datasets/WIDER_Face/WIDER_val/images/ \
--dataset_list datasets/WIDER_Face/wider_face_split/wider_face_val_bbx_gt.txt \
--pretrained_path models/img2pose_v1.pth \
--output_path results/WIDER_FACE/Val/
I also use eval tools provided by WIDER FACE to get the result of your publised model img2pose_v1.pth
,
Easy Val AP: 0.876
Medium Val AP: 0.855
Hard Val AP: 0.79
No matter which test script being used, model img2pose_v1.pth
can not achieve the precision of paper, begging for your advices, thanks so much!
from img2pose.
Hi @KindleHe,
I re-ran the evaluate_wider.py script using the img2pose_v1.pth model and got the same results as reported in our paper using eval_tools.
Did you change anything inside evaluation/evaluate_wider.py or are you using it as provided?
When you ran wider_eval.m, does it give you any error?
from img2pose.
Related Issues (20)
- Question about 300W-LP labels acquirements HOT 6
- Pose to angle HOT 1
- jaw data HOT 1
- Hi, I'm confused about the definition of the output pose HOT 1
- Slow inference HOT 2
- Question about Visualizing the Activation Map on each layer of the model HOT 1
- Question on fine-tuning HOT 1
- Question about Fine tuning Model with 300W-LP HOT 1
- Bug in readme file HOT 1
- img2pose_v1.pth convert onnx? HOT 1
- A Question about the conversion of t .
- A question about K_box and K_img. HOT 1
- A Question about fine-tuning HOT 2
- TypeError: a bytes-like object is required, not 'NoneType' HOT 4
- A Question about the 6DoF HOT 1
- A Question about the convert_to_aflw
- ONNX output is giving incorrect DOF values HOT 1
- How to get the tvec=[tx,ty,tz]?
- Utilizing GT intrinsics
- AFLW2000-3D translation
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 img2pose.