Comments (1)
We need to perform NMS on each timestep independently to avoid suppressing future detections from stationary objects. You may be able to modify the NMS code to take into consideration the timestep of each future prediction to avoid the issue described above so you only need to run NMS once.
I am currently working on a newer version of this code that is based on the mmdetection3d framework, supports nuScenes and Argoverse 2, and allows for multi-class FutureDet. I can try to address this problem here. I expect to release this in the next few days.
from futuredet.
Related Issues (18)
- Update the document for this project? HOT 3
- RuntimeError: Sizes of tensors must match except in dimension 2. Got 136 and 135 (The offending index is 0) HOT 5
- AssertionError: Samples in split doesn't match samples in predictions. HOT 1
- Test split HOT 4
- Probability of trajectories
- How to speed up training。
- The problem about batchsize and dataloader_num
- using MaP
- Is there an implementation for Trajectron++ and centerpoint?
- AV2 support
- res["lidar"]["bev_map"] : axes dont match array HOT 2
- Clues to solve ValueError: res["lidar"]["bev_map"] axes don't match array HOT 3
- Problems with training HOT 3
- Expect the re-implenmation in MMDetection3D HOT 2
- No such file or directory: 'models/FutureDetection/nusc_centerpoint_forecast_n3dtf_detection/metrics_summary.json' HOT 6
- Machine properties HOT 1
- RuntimeError: CUDA out of memory. HOT 2
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 futuredet.