Comments (2)
Thank you very much for your high performance repo!
I want to improve the recognition rate on my dataset, so I use the “backbone_ir50_asia.pth” you have released as the pretrain backbone model to retrain it, I update all the parameter of the backbone, but the val acc of calfw is only 56% even after 50 epochs. So I decide to only retrain the parameter of fc1 and fc2 of the backboned, do you think it will be used?
Can you give me some precious advice about how to improve the model's recognition rate on real scene and how should i do to finetune the pretrian backbone model?
thanks, good wishes for you!
Thank you for your question. May I know your LR during fine-tuning?
from face.evolve.
Thank you very much for your high performance repo!
I want to improve the recognition rate on my dataset, so I use the “backbone_ir50_asia.pth” you have released as the pretrain backbone model to retrain it, I update all the parameter of the backbone, but the val acc of calfw is only 56% even after 50 epochs. So I decide to only retrain the parameter of fc1 and fc2 of the backboned, do you think it will be used?
Can you give me some precious advice about how to improve the model's recognition rate on real scene and how should i do to finetune the pretrian backbone model?
thanks, good wishes for you!Thank you for your question. May I know your LR during fine-tuning?
I just start the training and don't change the LR in the config. the LR is 0.1 and epochs is 125. Now 60 epochs has ended. The training prec@1 is 94.7, training prec@5 is 96.8 and val acc of calfw is still 56%
from face.evolve.
Related Issues (20)
- Mistake in the focal loss implementation?
- convert model to tensorflow lite
- 戴口罩的人脸识别有做嘛?
- Could you please help with pretrained model of IR_SE_50?
- CFP aligned dataset HOT 1
- how to do inference on webcam? HOT 1
- How to implement the triple loss? HOT 1
- Private Asia Face Data
- paddle inference demo 无法运行 HOT 2
- quero ve fecha essa po
- ms1mv2
- Missing HEAD checkpoint file
- pretrained model seems wrong
- Can we use the pretrained models for commercial use?
- Slow training HOT 1
- does it support facial recognition with masks?
- How to make the Private Asia Face Data ?
- Accuracy, training loss is so bad
- how to set the margin of the face cropped after face alignment?
- 是不是粘贴错了什么东西(
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.evolve.