Comments (1)
Finding the best model is not as simple as saving the one that has minimum loss function. Sometimes when training for extremely long (thousands of epochs), the model can learn a better (more general) representation of the data without decreasing the loss function. I couldn't find where I learned this, but it was related to this theory: https://medium.com/@MITIBMLab/estimating-information-flow-in-deep-neural-networks-b2a77bdda7a7
Saving the model regularly is generally a good practice. We could add an option like "model_save_frequency". E.g. if it's 5 then the model would be saved after every 5 epochs using names like model_005, model_010, etc. And we could save on the wandb report all the metrics for each saved model.
I also had positive experience in the past training for a few hundred more epochs after it seemed like the metrics did not improve.
from aigt.
Related Issues (20)
- Where is the "Processes" modules? HOT 3
- Fix Slicer extension build HOT 1
- Question about Tutorial of Deep Learning Live module
- Dataset availability HOT 2
- Unable to access dataset and trained models HOT 4
- Resizing images in prepare_data vs. resizing using Pytorch Dataset HOT 1
- Dataset __getitem__ cannot return None
- Use metics from monai and put a table of final metrics on wandb HOT 2
- Use a couple of u-net variations from monai
- Add sequence processing mode to Torch Live Ultrasound
- Add augmentation for training
- train.py stopped logging into file and prints log in terminal HOT 1
- Support transforms that are only applied on the training data HOT 2
- Support images multiple segments HOT 1
- Add option to shuffle training data HOT 1
- Record performance metrics of each trained model
- Add scan conversion function and its inverse
- Single slice segmentation: mouse scroll should control timeline HOT 1
- Issue with Running prepare_data.py Script HOT 4
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 aigt.