GAP_SRAM

Introduction

This repo is the PyTorch implementation of (Group Activity Prediction with Sequential Relational Anticipation Model) in ECCV 2020.

Dependencies

• Python 3.x
• PyTorch 1.0.1
• numpy, pickle, scikit-image
• RoIAlign for Pytorch
• Datasets: Volleyball

Prepare Datasets

1. Download volleyball.
2. Unzip the dataset file into data/volleyball.

Get Started

```shell
python scripts/train_volleyball.py
```

You can specify the running arguments in the python files under `scripts/` directory. The meanings of arguments can be found in `config.py`

Note that part of codes are referred from (ARG) project.