Comments (2)
Thanks for your attention! The CAVIAR and MLR-VIPeR datasets are too small to get reliable results. Using fewer iteration steps (e.g., 1/3 of the original number of steps) may avoid overfitting and improve performance.
from degradation-invariant-reid-pytorch.
I tested it every epoch during training, and the best results I obtained were:
2023-08-19 23:45:27,157 reid_baseline.train INFO: ----------
2023-08-19 23:45:28,445 reid_baseline.train INFO: Validation Results - Epoch: 30
2023-08-19 23:45:28,445 reid_baseline.train INFO: mAP: 35.7%
2023-08-19 23:45:28,445 reid_baseline.train INFO: CMC curve, Rank-1 :42.8%
2023-08-19 23:45:28,446 reid_baseline.train INFO: CMC curve, Rank-5 :66.4%
2023-08-19 23:45:28,446 reid_baseline.train INFO: CMC curve, Rank-10 :78.4%
Could you please provide more details or share the weights file along with the dataset source file?
Thank you very much for your response!
from degradation-invariant-reid-pytorch.
Related Issues (5)
- Training code HOT 4
- Datasets HOT 1
- Person ID Split HOT 2
- Question regarding the performance on MSMT17
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 degradation-invariant-reid-pytorch.