Face Detection Based on Detectron2
A PyTorch implementation of RetinaFace: Single-stage Dense Face Localisation in the Wild. The official code in Mxnet can be found here.
Old version canbe found at v1.0
| Style | easy | medium | hard |
|---|---|---|---|
| Ours (Original Scale) | 94.14% | 92.71% | 81.13% |
pip install -e .
I've tested this code in 2080TI, the model forward just need about 0.008s, but the prior_box decode need about 0.14s. any advices to optimize this part?
I am trying this code in windows for cpu.
python setup.py build develop (from make.sh)
then get this error:
NotImplementedError: Cuda is not availabel
what should I do? THX
why mmdet is not the core of mmdetection？Detectron2 is detectron.....
Right now it is not possible to trace the model because of its reliance on _DCNv2.
RuntimeError:
Could not export Python function call '_DCNv2'. Remove calls to Python functions before export. Did you forget add @script or @script_method annotation? If this is a nn.ModuleList, add it to constants:
Hi, is the improvement of test results on widerface due to deformable convolution in SSH modules?
There are currently 2 versions of retinaface_mnet_025 in the insightface repo. Is this better than both of them?
Can you release the converted model so that I can test them?
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
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.
