Comments (1)
plemeri
commented on June 8, 2024
Hi, the purpose of saving model in this repository during training session is to resume training if the training stops unexpectedly. We only save every 20 epochs since it took only few minutes per epoch. However, it is a good idea to save best checkpoint by evaluating the model every epoch with validation dataset, but we do not consider to make validation dataset.
Moreover, I agree with the fact that it might not be the optimal checkpoint, but to be clear with the training setting for fair comparison on test benchmark, we only use the latest checkpoint. It would be cheating if we find and use checkpoints in the middle of training.
Thanks and happy new year to you too
from uacanet.
Related Issues (14)
- About SFA implementation HOT 3
- Results on ETIS-LaribPolypDB dataset HOT 3
- Clarification on pretrained weights HOT 1
- Could you please tell me how to get the CVC-300，CVC-ColonDB，ETIS dataset HOT 1
- A small question in Train.py
- The evaluation result is not good. HOT 11
- About this Baseline model HOT 4
- about "break" in train.py HOT 1
- about distributed training HOT 3
- Some questions about the ‘bce_iou_loss’ function HOT 2
- result problem HOT 1
- Some questions about Axial-attention HOT 7
- Multiple classes training HOT 2
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 uacanet.