Comments (10)
Hey guys, I have updated the repo.
from icnet-tensorflow.
Hey, @UndeadBlow , I have already done, now I am checking the performance.
from icnet-tensorflow.
Hey @HoracceFeng , I will provide the training code in recent days. What kinds of dataset do you want to use? Maybe I can give you some suggestions.
from icnet-tensorflow.
waiting for the train code
from icnet-tensorflow.
Hi, the datasets are some gray level images, and just have two classes.
from icnet-tensorflow.
waiting for the train code +1
And I just want to do perdestrian segmentation.
Because after I compared the provided checkpoint icnet model with fcn-8s in terms of perdestrian segmentation accuracy, it seems that the icnet model here do not show advantage and perform even worse than fcn_8s.
So, maybe i should train a specialized icnet model for perdestrian segmentation?
from icnet-tensorflow.
Hey, @ifangcheng , I think ICNet model focus on "real-time" segmentation, so it will get faster inference time at a sacrifice of accuracy. So, if you just want to do pedestrian segmentation, you can take PSPNet into your consideration, much slower but accurate. I have already implemented it too, you can take a look on it.
from icnet-tensorflow.
@hellochick, thanks for the suggestion.
However, real-time is also very important for me.
I suppose ICnet when trained specially for perdestrian segmentation may improve the accuracy than the provided model which is not focusing on perdestrian segmentation, am I right?
does that make sense?
from icnet-tensorflow.
Hi, @hellochick, any updates about train?
from icnet-tensorflow.
from icnet-tensorflow.
Related Issues (20)
- Errors in restoring the session evalucation.py and network.py
- ValueError: Shape must be rank 4 but is rank 3 for 'data_sub2' (op: 'ResizeBilinear') with input shapes: [720,720,3], [2]. HOT 3
- Why is it suddenly 'killed' run train.py? HOT 1
- How predict the result to use my training model ckpt.meta?
- Dimension not equal HOT 1
- ValueError:Variable conv does not exist
- ValueError when using own dataset HOT 2
- Training own dataset
- Inference time is too high(about 3.5x as supposed to be ~0.04s)
- multi GPU training?
- tensorflow's version HOT 1
- How to use the pre-trained modle of ade20k provided by author,I use the code in demo.ipynb,but it can't open the file,the cityscapes works well.
- Training over-fitting after every epochs
- same classification result with every pixel HOT 1
- can get correct result
- bad results of voc2012
- The update stops and the loss does not drop HOT 4
- Assign requires shapes of both tensors to match. lhs shape= [13] rhs shape= [150]
- 上一个项目
- 关于ade20k的分割结果,颜色和标签有对应关系吗?
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 icnet-tensorflow.