---
license: bsd-3-clause
tags:
- mirror
- xai
- video
- action-recognition
- kinetics-400
---

# R3D-18 Kinetics-400 (torchvision) — xaitalk mirror

This is a **bit-identical mirror** of the canonical artifact from PyTorch / torchvision.

The mirror exists only as a resilience fallback for the
[xaitalk](https://github.com/xaitalk/xaitalk) library — the upstream remains
authoritative. All credit and licensing for the model belong to the original
authors.

## Attribution

| Field | Value |
|---|---|
| **Original authors** | PyTorch / torchvision |
| **Upstream (authoritative)** | https://download.pytorch.org/models/r3d_18-b3b3357e.pth |
| **Source repo** | https://github.com/pytorch/vision |
| **Paper** | https://arxiv.org/abs/1711.11248 (Tran et al. 2018, A Closer Look at Spatiotemporal Convolutions) |
| **License** | `bsd-3-clause` (inherited from upstream — please respect upstream's terms) |
| **Mirror file** | `r3d_18-b3b3357e.pth` |
| **SHA-256** | `b3b3357ead25631ec9c57362ff2128a92d0427e01e2cd184951a44380c3f2e9d` |
| **Size** | 133,546,016 bytes (127.4 MB) |

## How xaitalk loads this file

```python
from xaitalk.hub import ensure_model
weights_path = ensure_model("r3d18-kinetics400")
# Tries the canonical upstream first; falls back to this xaitalk mirror
# automatically if upstream is unreachable.
```

## Why mirror?

xaitalk's research-grade reproducibility claim relies on every weight file
being recoverable years from now. We mirror artifacts ≤ 2.5 GB under
`xaitalk/*-mirror` so the pipeline survives upstream URL changes, repo
renames, or deletions. Bit-level parity with the canonical is asserted in
CI via `python -m xaitalk.hub verify-mirrors`.

## Citation

If you use this model, **please cite the original paper** (not the mirror):

```
https://arxiv.org/abs/1711.11248 (Tran et al. 2018, A Closer Look at Spatiotemporal Convolutions)
```