Comments (8)
@william-gx The code for deriving the yaw predictions can be found here:
Line 53 in c8a57e5
@RLuke22 Many thanks for your reply and the code.
from fjmp.
Hi Chengkai,
To reproduce our results on the INTERACTION leaderboard, we retrain the models with both the train+validation datasets and use the checkpoint at the final epoch to build our submission. As the INTERACTION leaderboard is now open again, I will include the code to build the submission file (including how to derive the yaw predictions). This will be pushed in the next week - thanks for your patience.
from fjmp.
Hi Chengkai,
To reproduce our results on the INTERACTION leaderboard, we retrain the models with both the train+validation datasets and use the checkpoint at the final epoch to build our submission. As the INTERACTION leaderboard is now open again, I will include the code to build the submission file (including how to derive the yaw predictions). This will be pushed in the next week - thanks for your patience.
Hi, Luke,
I found INTERACTION dataset's challenge benchmark might not exists now (website can't be open in my computer). When I try to open the leaderboard, the competition url page, http://challenge.interaction-dataset.com/prediction-challenge/intro got crashed. Have you met the same problem? If not, could you please tell me the correct challenge url? I would like to know does INTERACTION challenge use a new url which might be different from the old one? Thanks!
from fjmp.
Hi Chengkai,
To reproduce our results on the INTERACTION leaderboard, we retrain the models with both the train+validation datasets and use the checkpoint at the final epoch to build our submission. As the INTERACTION leaderboard is now open again, I will include the code to build the submission file (including how to derive the yaw predictions). This will be pushed in the next week - thanks for your patience.Hi, Luke, I found INTERACTION dataset's challenge benchmark might not exists now (website can't be open in my computer). When I try to open the leaderboard, the competition url page, http://challenge.interaction-dataset.com/prediction-challenge/intro got crashed. Have you met the same problem? If not, could you please tell me the correct challenge url? I would like to know does INTERACTION challenge use a new url which might be different from the old one? Thanks!
Yes, I'm facing the same problem, unfortunately. I will still release the test submission code in case the INTERACTION leaderboard goes live again.
from fjmp.
Hi Chengkai,
To reproduce our results on the INTERACTION leaderboard, we retrain the models with both the train+validation datasets and use the checkpoint at the final epoch to build our submission. As the INTERACTION leaderboard is now open again, I will include the code to build the submission file (including how to derive the yaw predictions). This will be pushed in the next week - thanks for your patience.Hi, Luke, I found INTERACTION dataset's challenge benchmark might not exists now (website can't be open in my computer). When I try to open the leaderboard, the competition url page, http://challenge.interaction-dataset.com/prediction-challenge/intro got crashed. Have you met the same problem? If not, could you please tell me the correct challenge url? I would like to know does INTERACTION challenge use a new url which might be different from the old one? Thanks!
Yes, I'm facing the same problem, unfortunately. I will still release the test submission code in case the INTERACTION leaderboard goes live again.
Thank you so much!
from fjmp.
@RLuke22 Hi Luke, we notice that the INTERACTION leaderboard opens again. Could you kindly release the test submission code, especially code for deriving the yaw predictions. Many thanks.
from fjmp.
@ChengkaiYang @william-gx Sorry for the delay on this. The repository is now updated with the INTERACTION test submission code, with instructions in the README.
from fjmp.
@william-gx The code for deriving the yaw predictions can be found here:
Line 53 in c8a57e5
from fjmp.
Related Issues (7)
- When will the code be released? HOT 1
- about 《FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-tail Trajectory Prediction》code HOT 2
- Model Checkpoints HOT 1
- There is no command provided here for training on the Argoverse 2 dataset using a single GPU. HOT 1
- Argoverse2 Leaderboard HOT 2
- Problems about horovod run HOT 10
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 fjmp.