Comments (1)
The default setting in provided codes is different from that in FPointNet's official repo, especially for the training schedule. We use some different strategies for faster convergence. For pseudo-LiDAR, it can accelerate training and get the same or better results, while the performance of FPointNet is slightly reduced (~0.7 AP). If you want to reproduce the performance reported in the FPointNet paper, you can try to adjust the training schedule.
from patchnet.
Related Issues (20)
- Unable to convergence HOT 3
- the performance of pretrained model HOT 1
- One Question abou rotato_patch_to_center HOT 2
- patchnet train_val.py
- Connent pseudo-lidar and patchnet
- box2
- box2d HOT 7
- 关于fpoinnet和pseudo-lidar HOT 3
- Can PatchNet be used to do distance measurement? HOT 2
- 2D detector HOT 2
- rect_to_img in calibration.py
- Question regarding lib/models/patchnet.py HOT 2
- The result I train the model from the github code is different with your paper, drop 1.2%. HOT 2
- How to generate the test set pkl data? HOT 1
- About adding new backbone HOT 1
- When could I use add_rgb? HOT 1
- Questions about the KITTI datasets HOT 2
- Errors when running " python ../../tools/train_val.py --config config_patchnet.yaml"
- code for this paper
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 patchnet.