Comments (8)
Hi! That's interesting, could you provide your testing code and more info about models you have tested?
from insightface-rest.
So i just used the test pairs .txt file provided in their website and then run your onnx arcface model that was produced by running your docker using onnxruntime. and then check the results on various thresholds.
I noticed that you converted the model from mxnet. would there be a difference in the result if we convert the pytorch model into onnx?
from insightface-rest.
Have you tested same code with backend set to mxnet?
The accuracy drop you mentioned is way too large, it might be caused by improper validation, as well as some massive bug in my code, but such accuracy drop should be easily noticable in most use cases.
I haven't tested torch models yet.
from insightface-rest.
Okay let me double check and re-run the code then.
from insightface-rest.
Any updates?
from insightface-rest.
Hi, sorry for the late update, I still find the same result for mobilenet retinaface + arcface resnet100. However. yesterday I just tried the onnx models that was uploaded in insightface (antelope) containing scrfd 10g and arcface resnet100 glint, and I got 0.9985 accuracy on threshold==0.26 on LFW test set. So, I think the newer models are better.
from insightface-rest.
Are you sure that correct preprocessing was used for older models? If I understand you right, you used onnx models in your own code?
from insightface-rest.
It is certainly a possibility that I screwed up somewhere. I tried to translate the python code to c++ version and ran a test on it. One suspicion that I have is that I installed the wrong onnx/mxnet version because I did not use your docker. Anyway, I think the issue is solved now. So I am going to close this issue.
from insightface-rest.
Related Issues (20)
- How to use docker swarm hostname instead of localhost? HOT 2
- deploy_trt.sh closes while executing, server couldn't start HOT 3
- Buffalo support HOT 3
- ValueError when using the CPU build via Docker HOT 1
- ValueError: could not broadcast input array from shape (75264,) into shape (37632,) HOT 1
- rtsp stream HOT 1
- Gpu Quatro RTX 5000 error HOT 1
- onnx vs trt HOT 1
- What is the workflow to add a new model? HOT 2
- Thankyou for excllent work. I am able to run demo_client but please i want to know how i can select the model of my choice or put custom trained model. HOT 1
- Thank you for excllent work. How about TRT batch inference? HOT 1
- scrfd 10 false positive HOT 1
- Support for coordinate and synthetic mask models (landmark_2d_106 , landmark_3d_68) HOT 3
- Hash Mismatch HOT 1
- [ERROR] Exception in ASGI application HOT 1
- [ERROR] Exception in ASGI application HOT 4
- Error when run deploy_trt.sh - google.protobuf.message.DecodeError: Error parsing message
- What is the difference between scrfd_10g_bnkps and scrfd_10g_gnkps HOT 7
- KeyError: 'score_8' in trt_backend.py (called by scrfd.py) when running demo scripts with scrfd_10g_gnkps and glintr100 HOT 2
- deploy_cpu and deploy_trt scripts need to be updated due to recent changes 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 insightface-rest.