Comments (3)
Hello,
Good catch. After reading the paper I decided that the easiest way to do exactly the same network was to use their code, for a fair comparison. When I did, I did not see that discrepancy. But if you look here https://github.com/BichenWuUCB/SqueezeSeg/blob/master/src/nets/squeezeSeg.py , it looks like the author in the code is using squeeze*4 everywhere. Only some layers keep the dimensions.
I do not recommend using squeezeseg for the semantic kitti dataset. Go for one of the darknet backbones, they achieve significantly higher IoU.
Closing this, as it is not an issue. But feel free to keep commenting
from lidar-bonnetal.
Yeah, I also try the Darknet, how about the Focal loss they claim in the SqueezeSegV2 paper? Do you use it in this code?
from lidar-bonnetal.
I tried it, but it did not make a lot of difference vs inverse frequency scaling. That is very dataset dependent...
from lidar-bonnetal.
Related Issues (20)
- Expected object of scalar type Long but got scalar type Int for argument #2 'target'
- Question about speed after tensorrt of rangenet++ HOT 2
- Possibility of rosifying the process HOT 1
- No error or no visualizations when executing the viusalization.py file
- Questions about the learning setting HOT 1
- Where are the pretrained models HOT 4
- Inference, and training not working on Semantic KITTI dataset. HOT 2
- index the unused points HOT 1
- KNN HOT 1
- Module not found error when running the infer function to get the prediction.
- RangeNet++
- tensorflow / cuda / python versions for 22.04/20.04 HOT 2
- How to create cali.txt and pose.txt data from custom data HOT 1
- about the dataest HOT 2
- KNN HOT 1
- Why in all arch settings, KNN is disabled? HOT 1
- point de-skewing HOT 1
- Where do the values in arch_cfg.yaml file come from, especially fov_up, fov_down, img_means, img_stds? HOT 4
- IndexError HOT 2
- Stop-gradients in skip-connections 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 lidar-bonnetal.