Comments (1)
Hi,
Thanks for the feedback. I'll work out more examples in the next release. You can use the same losses as in the HoVer-Net paper if you wish but the idea in this repo has been to write the code flexibly so that ppl could train the models as they wish. The loss defaults are pretty basic so you might want to adjust them to your needs. Also, in the HoVer-Net paper they used their own grad-MSE loss which was the just the MSE taken from the gradient of the gt-mask and the model prediction. I implemented it but learned pretty quickly that it blew up the gradients easily so I've just ignored it thus far. I might try to rewrite in the future..
from cellseg_models.pytorch.
Related Issues (10)
- Data preparation issue HOT 2
- AttributeError: type object 'FileHandler' has no attribute 'read_mask' HOT 1
- Training Problem HOT 15
- Data preparation issue HOT 6
- using pretrained weights HOT 2
- I need help please
- Segmentation output issues HOT 5
- Could you provide pretrained weight? HOT 2
- pannuke_datamodule.py is different between your installed package and github code. 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 cellseg_models.pytorch.