Comments (2)
Upon further inspection it seems that the error occurs when the there are too few points(1 or 0) in input_data['radar_points']
. Could you suggest a fix to this?
from radar_depth.
Hi @isht7
The ver2_lidar1_radar3_radar_only is more like a patch for more radar information. In ver3, if I remember correctly, I used only the front and back camera + Radar points, but we accumulate the radar points along the temporal axis a bit to get more points.
Regarding the ver2 issue, as I indicated in README.md, I haven't finished the documentations on dataset yet. The processed dataset was originally extracted from the nuScenes database. The code used to export them can be found here. However, I haven't tested them before the release of the code (I don't have the machine and storage to do that now since students need to leave the lab after the project). The top priority in this repo is that the users can used the training code and processed dataset to get the similar results I got on the paper.
Regarding the projection of radar points onto other camera, you can check the code here and try it yourself. I remember that you can't get like more than 10 points which is quite frustrating. That's the reason why I changed back to front + back views.
from radar_depth.
Related Issues (19)
- Awesome! HOT 1
- Without lidar HOT 5
- Evaluation error args = checkpoint['args'] HOT 7
- Visualization HOT 1
- About the pretrained argument HOT 2
- Can not evaluate provided pretrained models HOT 1
- Question about ref_chan in radar multisweep HOT 1
- max_depth or max-depth?
- can you release your dataset? HOT 1
- Evaluation of Pretrained Models
- Detailed documentation for the processed dataset.
- Release date HOT 13
- How to obtain ground truth depth image? HOT 3
- Questions about hyperparameters and processed dataset HOT 7
- Question on the RGB - Radar alignment issue HOT 5
- Bidirectional radar sweeps HOT 2
- About train / val scene numbers HOT 2
- Own dataset make method 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 radar_depth.