Comments (1)
TobyPDE
commented on August 22, 2024
Data augmentation is exceptionally important if you train from scratch. At the moment, I'm even retraining the models with a more extensive data augmentation pipeline. I have already released the retrained FRRN A model. The FRRN B model will follow soon together with the updated code.
If you train without data augmentation, you will observe significantly lower IoU scores on the validation and test sets.
from frrn.
Related Issues (20)
- Error running predict_frrn_a.py with the prerequisites mentioned in README HOT 1
- what is the point of chinati library? HOT 1
- Runnin predict without cityscape HOT 7
- Dependency Version Requirements? HOT 1
- input image is black HOT 3
- training batch size HOT 1
- Error Running predict on cityscapes with python 2.7 HOT 2
- The questions about prediction HOT 1
- init model HOT 2
- Chianti TypeError in train.py l264 HOT 2
- Dimensionality reduction before last RU's
- train with smaller image resolution
- Trying to evaluation with non cityscape image HOT 2
- ERROR Cannot create cuDNN spatial log softmax. HOT 1
- Adding in associative memory to the network structure
- Getting from cudnn HOT 1
- Predict on own image
- cuDNN spatial log softmax and Chianti C++ library HOT 3
- predict error: IndexError
- Theano and Lasagne version
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 frrn.