Comments (1)
In my opinion, scaler.step(optimizer) include unscaleing and it do two things,first unscaling if you did't unscale manualy before.second,it will check if there exists overflows,if there are no NAN/INF,it will execute the optimizer's step,if there are,it will skip this iteration's parametes update.so if the gradients are clipped after the scaler.step,I think it make no sense.the gradients clip just aim to avoid gradient explosion,but if there exist gradinent explosion ,scale.step will skip this iteration's parametes update,abosolutely there in no need for clipping.
from pytorch-unet.
Related Issues (20)
- How to add data augmentation into dataset before training? HOT 2
- torch is not detecting any cuda. HOT 9
- predict.py
- Using Per Class IoU to evaluate trained model
- Always [0,1] mask on mutil-classes models HOT 1
- Refer the datasets to download from Kaggle
- Windows .bat setup script HOT 1
- Latest Python versions have deprecated `distutils` module
- How to accurately calculate Model Parameters and GFLOPs?
- thanks a lot, your model help me lot, I make a grad-cam to mark what place the U-Net look, also named hot-map HOT 1
- The training loss is always nan. HOT 3
- dice = ? 0.5
- miou and acc
- 为什么预测出来的图片全黑,能不能回复一下 HOT 3
- can't change batch_size
- IndexError: list index out of range
- Python version HOT 1
- My own dataset reported an error
- Did you use "crop" in the skip connection? or you just connect them? 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 pytorch-unet.