Khrylx/AgentFormer
[ICCV 2021] Official PyTorch Implementation of "AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting".
This project helps predict the future movements of multiple agents, like pedestrians or vehicles, in shared spaces. It takes historical movement data as input and outputs probable future trajectories for each agent. This is useful for researchers and engineers working on autonomous systems or crowd management.
309 stars. No commits in the last 6 months.
Use this if you need to accurately forecast the paths of multiple interacting entities, such as people in a crowd or cars on a road.
Not ideal if your task involves predicting the movement of a single agent or requires real-time, ultra-low-latency predictions for safety-critical systems.
Stars
309
Forks
71
Language
Python
License
MIT
Category
Last pushed
Oct 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Khrylx/AgentFormer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...