Comments (6)
from ademxapp.
Hi.
First of all. I am not the owner of the code. But I have faced the same issue.
I think the work around is change the sum metric to dice score (f1). I have not managed to make it work jet.
from ademxapp.
Hi Christian, can you reference the location in the code that you recommend to change and optionally how you recommend to change it (even if its not working right now)?
from ademxapp.
Line 456 in voc.py defines the metric function "_get_metric()"
Currently, it uses a custem metric function "CustomMetric" defined in line 336-346 in voc.py
The F1 metric function is suitable for the case of binary segmentation. (https://github.com/dmlc/mxnet/blob/master/python/mxnet/metric.py)
The metric function should be changed to this. Alternatively, one could change to a log likelihood cost function with a greater weight class 1.
from ademxapp.
@ChristianEschen cool i will give it a try later the day. You said "I have not managed to make it work jet." => Does it mean you didn't get the metric replaced (= programming issue) or did the training not converge (= training issue)?
from ademxapp.
from ademxapp.
Related Issues (20)
- Errors in full image test on cityscapes val dataset HOT 2
- Scale rates of multiscale test in cityscapes HOT 2
- How to run the semantic segmentation on my own images? HOT 11
- Simple_bind error HOT 3
- Pretrained models for cityscape needed HOT 3
- Training command required to train semantic segmentation on cityscape dataset...
- How can I train a model with 2 classes?
- Training script for semantic segmentation VOC2012 HOT 1
- how to get coco20 png annotations
- Only got 76.90% over Pascal VOC2012 val set HOT 5
- What's the difference of the model a2 and a
- Experimental setting for training ADE20K?
- MxNet, Python, CUDA, CUDNN versions HOT 2
- multi-steps testing~
- Where to get pretrained city scape model (cityscapes_rna-a1_cls19_s8_ep-0001.params)? HOT 4
- The parameter for training VOC 2012 dataset
- pre-trained model in ade20k HOT 1
- Training on VOC from Scratch HOT 2
- the predicted image is all black using trained model on VOC
- pre-training files for resnet38? 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 ademxapp.