Comments (9)
It is hard to provide a general solution for all datasets. However, as I know, some researchers achieve amazing results on some custom datasets with multiple categories (approach fully supervised results) with a few adjustments to ST3D. Hence I believe that ST3D should work for other datasets with multiple categories, but need some tuning of hyper-parameters.
from st3d.
I fixed the bugs on multi-category and got good performance on multi-category. Thank you very much! Could you please tell when will you release the code for ST3D++?
from st3d.
Happy to heard that! We don't have a clear plan to release the code since the paper is still in submission. BTW, the techinical modification of ST3D++ is not significant, may be I can support DSNorm and SASD in this repo later. I believe that it should be easy to reproduce our results.
from st3d.
Thank you very much! I would like to see DSNorm and SASD as soon as possible!
from st3d.
For further research, I want to learn from the DSNorm and SASD. Could you please send me the code contains the DSNorm and SASD by email? Thank you very much!
from st3d.
Hello !
I am very interested in your solution for multi-category ST3D as I am working on a similar problem, is there any way you could send it to me by email please ?
Thanks a lot !
from st3d.
Hello ! I am very interested in your solution for multi-category ST3D as I am working on a similar problem, is there any way you could send it to me by email please ? Thanks a lot !
You need to change the pred_labels for ignore in
ST3D/pcdet/utils/self_training_utils.py
Line 191 in 68a9d3e
ST3D/pcdet/datasets/dataset.py
Line 152 in 68a9d3e
from st3d.
Excuse me, may i ask ask how to modify the code specifically, applied to multi-class pre-training and multi-class ST3D training
from st3d.
Hello ! I am very interested in your solution for multi-category ST3D as I am working on a similar problem, is there any way you could send it to me by email please ? Thanks a lot !
You need to change the pred_labels for ignore in
ST3D/pcdet/utils/self_training_utils.py
Line 191 in 68a9d3e
and others. And change the code for loading pseudo labels of multi-categories in
ST3D/pcdet/datasets/dataset.py
Line 152 in 68a9d3e
and others.
Excuse me, may i ask how to modify the code specifically, applied to multi-class pre-training and multi-class ST3D training. Or just need to change the top two lines pred_labels[ignore_mask] = -1 gt_names = np.array([self.class_names[0] for n in gt_boxes])
from st3d.
Related Issues (20)
- 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.
- The config file for multi classes training
- attempt to write config kitti -> nuscenes(mini)
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.