Comments (2)
Hi, all the experiments are conducted on one NVIDIA 1080Ti GPU. The training epoch is empirically set to 300. In fact, according to the best performance, the training epoch is around 200 for the fully supervised setting and around 30 for the weakly supervised setting.
The total training process is normally not more than 1 hour.
It seems that we do not set the early stopping, you can refine the codes accordingly. Also if you want to train from scratch, you may make some adjustments as introduced in README.
from psp_cvpr_2021.
Thanks for your answer!
from psp_cvpr_2021.
Related Issues (11)
- data HOT 2
- Some questions about the paper HOT 1
- Train from scratch HOT 3
- The question of result HOT 2
- Why do some Linear layers have bias set to False? HOT 1
- what information is prob_label.h5 generated based on HOT 2
- How to generate attention map? HOT 2
- Why the right_labels.h5 does not contain all the video labels? HOT 1
- weakly_model.py
- 如何在特征提取时获得4143组数据特征而不是4097组 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 psp_cvpr_2021.