Comments (5)
Maybe change of GRID_BOUNDS will work, i'll close this issue~
from vision3d.
Maybe change of GRID_BOUNDS will work, i'll close this issue~
sadly, it does not work, although i change GRID_BOUNDS to [-80, -40.0, -3, 80, 40.0, 2] both in training and inference
from vision3d.
Hmm, I'm not sure why this would happen. I think the only part of the code that would affect this is here. Also this issue seems to suggest there is no problem with 360 degree inference. Maybe you accidentally load the ckpt from the model trained before grid_bounds fix?
from vision3d.
if you only train on KITTI dataset, the result is normal, because the kitti annotations only exist in camera coordinates, which means only detect things only in front of the car.
If you want to detect 360 degree things:
- try to use Sample Augmentation, make every input training cloud have annotations in 360 degree.
- just train on other dataset like Nuscenes.
- do the inference twice for ahead 180 degree and rear 180 degree.
@eraofelix
from vision3d.
Hi, can you explain more about the third alternative - inference twice one? Do you mean flipping the whole input pointcloud? How would that work?
from vision3d.
Related Issues (20)
- future reproduce plan for PV-RCNN refinement layer HOT 12
- Data in 'inference.py' HOT 2
- Which GPU did you use? HOT 7
- please, how can I train the network with my own point cloud dataset? HOT 2
- Running 'train.py' HOT 11
- problem with spconv HOT 3
- Error about running "train.py" HOT 2
- Recall of RPN stage HOT 1
- Abour the GPU memory using HOT 5
- about the cls_loss and reg_loss compute
- Should grid point randomly sampled or evenly distributed HOT 1
- Nvcc fatal error: unknown option 'openmp '
- FPS when detecting HOT 1
- Bbox conversion HOT 1
- Evaluation HOT 1
- [Question] data format support HOT 1
- Yaw to rot_y conversion HOT 3
- What is the 'LOC function'? HOT 1
- Some problem in TargetAssigner HOT 4
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 vision3d.