Comments (4)
Update:
I also test the model PartA2_fc
provided in the README, which gives a similar result.
Class | Original Paper | Pretrained Model |
---|---|---|
Pedestrian | 70.37, 63.84, 57.48 | 62.8704, 56.3679, 50.1842 |
Cyclist | 88.31, 73.07, 70.20 | 86.9893, 71.3273, 68.3141 |
from openpcdet.
This results is as expected for 3 classes of a the single model. Training pedestrian/cyclist with separate models and also modifying the config generally achieve better results. Also the performance of pedestrian/cyclist is not stable on KITTI dataset, and the released codes have been highly refactored and I mainly focus on car objects to tune the performance. You could also try to use a general classification loss instead of the IoU loss for tuning pedestrian, which generally achieve better results.
from openpcdet.
@sshaoshuai Thanks for your reply!
Could you please suggest how to modify the config file to reproduce the result in the paper except training in a separate model for ped/cyc and general classification loss?
from openpcdet.
Actually the cyclist is easier than pedestrian, I just try to train the cyclist with more times, and the performances between training cyclist with a single model or joint with car are similar. For the pedestrian, you could also try to upsample the BEV feature map to 4x for putting anchors as pedestrain has smaller size. Finally, I found the fact was that the anchor-free version (PartA2-free which generates proposals like PointRCNN) achieves better and more stable results on pedestrian/cyclist on KITTI dataset.
from openpcdet.
Related Issues (20)
- The training phase of train.py shows epochs: 0it [00:00, ?it/s]. HOT 1
- Low Acc on 3D task, in Custom datasets. HOT 3
- training with pvrcnn losses not decreasing as seen in the tensor-board !!!! HOT 2
- pointpillar_newaugs.yaml can not use. HOT 2
- Adding MPPNet support for NuScenes HOT 2
- Visualizing the results
- Error when running demo.py HOT 2
- About BaseBEVBackbone HOT 2
- How to get validation loss and display it in Tensorboard HOT 4
- Abnormal demo.py result using nuscenses dataset pre-trained models HOT 3
- Ensemble or test-time augmentation? HOT 2
- free(): double free detected in tcache 2 HOT 2
- questions about GETTING_STARTED.md HOT 2
- 'EasyDict' object has no attribute 'BACKUP_DB_INFO' HOT 3
- What should we set the overlap values for custom datasets? HOT 5
- TypeError: expected str, bytes or os.PathLike object, not NoneType HOT 1
- `pillar_features` IndexError: too many indices for tensor of dimension 1 HOT 1
- Question about adam_onecycle optimizer HOT 2
- PV RCNN++ pretained model HOT 1
- [Docs] A100算力加持!书生大模型实战营第3期全面升级,趣味闯关模式等你开启 HOT 1
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 openpcdet.