---
license: mit
tags:
  - computer-vision
  - object-tracking
  - sports
  - volleyball
  - tracknet
library_name: pytorch
pipeline_tag: object-detection
base_model: qaz812345/TrackNetV3
---

# Beach Volley Vision — Fine-tuned TrackNetV3 (Ball Tracking)

A fine-tuned [TrackNetV3](https://github.com/qaz812345/TrackNetV3) model for tracking the
**ball in beach volleyball** footage. TrackNetV3 is a heatmap-based tracker designed for
small, fast-moving sports objects (originally shuttlecocks); this checkpoint adapts it to
the beach volleyball domain.

This is a **derivative** of the upstream TrackNetV3 model, fine-tuned on hand-annotated
beach volleyball rally clips. The upstream project is MIT licensed, and this derivative
carries the same license forward (see [License](#license)).

## Model details

- **Architecture:** TrackNetV3 (trajectory-prediction module). This repo contains the
  fine-tuned `TrackNet` weights only.
- **Base model:** [`qaz812345/TrackNetV3`](https://github.com/qaz812345/TrackNetV3)
- **Task:** per-frame ball localization (heatmap → (x, y) + visibility)
- **Domain:** beach volleyball match video
- **File:** `tracknet_best.pt` (~130 MB)

> **Note on InpaintNet:** the trajectory-rectification (inpainting) module was **not**
> retrained. If your pipeline uses it, download `InpaintNet_best.pt` from the
> [upstream TrackNetV3 repo](https://github.com/qaz812345/TrackNetV3).

## Usage

This checkpoint is consumed by the **Beach Volley Vision** pipeline:
👉 https://github.com/ddecks/beach-volley-vision

```bash
# Download the fine-tuned weights (git-lfs required)
git lfs install
git clone git@hf.co:deadfast/beach-volley-vision-models
# or grab the single file:
#   https://huggingface.co/deadfast/beach-volley-vision-models/resolve/main/tracknet_best.pt

# Place it where the pipeline expects it
mkdir -p data/models
cp beach-volley-vision-models/tracknet_best.pt data/models/tracknet_best.pt
```

See the [project repository](https://github.com/ddecks/beach-volley-vision) for the full
inference pipeline (detection → tracking → rally/event detection → stats).

## Training data

Fine-tuned on hand-annotated beach volleyball rally clips — frames labeled with ball
position and visibility, exported to the TrackNet CSV format
(`Frame,Visibility,X,Y`). Example annotation and evaluation data is included in the
project repository under `data/`.

## License

MIT — carried forward from the upstream
[TrackNetV3](https://github.com/qaz812345/TrackNetV3) project
(Copyright (c) 2024 qaz812345). Fine-tuning and beach volleyball adaptation by Devin Decker.

## Acknowledgements

- [TrackNetV3](https://github.com/qaz812345/TrackNetV3) by qaz812345 — the base architecture
  and pretrained weights this model is fine-tuned from.