Comments (3)
We just use an old version of waymo anchor size in openpcdet. KITTI anchor size has also been attempted but no gains are found.
from st3d.
We only try your second attempts "For the SN case changing the anchor size to KITTI mean didn't achieve anything for me as well". I think your result is reasonable. Since the model just learn to regress the offset of prediction according to the anchor size, changing the anchor size during eavluation is kind of similar to change the mean size of object.
from st3d.
@jihanyang thanks for the answer. Moreover, according to my experiments, using no SN/ROS WAYMO trained model updated with KITTI anchor size (during eval) achieves similar results to SN-WAYMO pre-trained model's performance on KITTI test set. However, keeping the WAYMO anchor size reduces performance a lot.
For the SN case changing the anchor size to KITTI mean didn't achieve anything for me as well.
from st3d.
Related Issues (20)
- Question about loss for ignored boxes HOT 6
- Waymo -> Kitti, evaluation error in source HOT 5
- Pretrain on waymo data HOT 2
- About pretrained weights for ST3D++ - PVRCNN HOT 1
- Evaluation on Lyft for paper result HOT 2
- Question about pretrained model HOT 1
- Unstable performance HOT 4
- Source Only and SN training HOT 13
- Have you ever tried ST3D on PointPillars? HOT 2
- Can this project be implement in openpdet-v0.6 HOT 10
- AttributeError: 'DataAugmentor' object has no attribute 'random_object_scaling' HOT 9
- AttributeError: 'EasyDict' object has no attribute 'FOV_DEGREE' HOT 4
- The Car [email protected], 0.70, 0.70 IS 0
- The code hangs on during multi GPU training HOT 8
- The cost definition for SASD HOT 1
- Performance of Nuscenes2KITTI HOT 3
- RecursionError: maximum recursion depth exceeded while calling a Python object
- RecursionError: maximum recursion depth exceeded while calling a Python object HOT 2
- what is the purpose of data augmentation in the target domain? HOT 4
- How to set source batch and target batch to fetch data as the data order in ImageSets.
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 st3d.