Metadata-Version: 2.1
Name: video-representations-extractor
Version: 1.18.2
Summary: Video Representations Extractor (VRE) for computing algorithmic or neural representations of each frame.
Home-page: https://gitlab.com/video-representations-extractor/video-representations-extractor
License: MIT
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE.TXT
Requires-Dist: loggez>=0.8.4
Requires-Dist: numpy>=1.21.6
Requires-Dist: PyYAML==6.0.3
Requires-Dist: tqdm==4.66.5
Requires-Dist: overrides==7.7.0
Requires-Dist: Pillow==11.3.0
Requires-Dist: graphviz==0.20.3
Provides-Extra: core
Provides-Extra: repository
Requires-Dist: torch==2.8.0; extra == "repository"
Requires-Dist: torchvision==0.23.0; extra == "repository"
Requires-Dist: opencv-python==4.12.0.88; extra == "repository"
Requires-Dist: pycocotools==2.0.10; extra == "repository"
Requires-Dist: timm==1.0.9; extra == "repository"
Requires-Dist: diffusers==0.30.3; extra == "repository"

# Video Representation Extractor

![logo](logo.png)

Documentation at: [link](https://video-representations-extractor.gitlab.io/video-representations-extractor/).

### Installation

```python
conda create -n vre python=3.11 anaconda # >=3.10 tested
pip install video-representations-extractor
[VRE_DEVICE=cuda CUDA_VISIBLE_DEVICES=0] vre example/video.mp4 --connfig_path example/cfg.yaml -o example/
```

For more details, see usage and installation page: [link](https://video-representations-extractor.gitlab.io/video-representations-extractor/guide/introduction_and_installation.html).

### Google Colab examples

- Batched VRE: Full example from a single test video to complex extracted representations: [link](https://colab.research.google.com/drive/1vAp71H-TLewhF56odv33TkmGwwhuoFJ-?usp=sharing)
- Streaming VRE: Real time Semantic Segmentation on youtube videos: [link](https://colab.research.google.com/drive/1-Zc7qEC7k7KnCuq-LOnNy9hoMfQBJA9O#scrollTo=TR5G9bBhY9_k)
