Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Python library for analysing faces using PyTorch
| Date | Stars |
|---|---|
| 2026-07-30 | 610 |
| 2026-08-27 | 610 |
| 2026-08-28 | 611 |
| 2026-09-04 | 611 |
| 2026-09-15 | 612 |
| 2026-09-20 | 613 |
| 2026-09-23 | 612 |
| 2026-10-10 | 611 |
| 2026-10-11 | 612 |
| 2026-10-28 | 613 |
| 2026-10-29 | 614 |
| 2026-11-04 | 614 |
Today
— stars today
This week
+1 stars this week
This month
+2 stars this month
Momentum
1.0
growth rate 0.16%/day
#  facetorch   [](https://pypi.org/project/facetorch/) [](https://anaconda.org/conda-forge/facetorch) [](https://raw.githubusercontent.com/tomas-gajarsky/facetorch/55fa112fce2708fdc1bee318e06dfd0e9758f612/LICENSE) <a href="https://github.com/psf/black"><img alt="Code style: black" src="https://img.shields.io/badge/code%20style-black-000000.svg"></a> <a target="_blank" href="https://colab.research.google.com/github/tomas-gajarsky/facetorch/blob/main/notebooks/facetorch_notebook_demo.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a> [API documentation](https://tomas-gajarsky.github.io/facetorch/facetorch/index.html), [extension guide](https://github.com/tomas-gajarsky/facetorch/blob/d73b8b1af1ff0f53dcb480ce2602c11ef908b815/docs/custom-components.md), [v0.6.x migration guide](https://github.com/tomas-gajarsky/facetorch/blob/d73b8b1af1ff0f53dcb480ce2602c11ef908b815/docs/migration-v1.md), [model compatibility](https://github.com/tomas-gajarsky/facetorch/blob/d73b8b1af1ff0f53dcb480ce2602c11ef908b815/docs/model-compatibility.md) [Docker Hub](https://hub.docker.com/repository/docker/tomasgajarsky/facetorch) [(GPU)](https://hub.docker.com/repository/docker/tomasgajarsky/facetorch-gpu) **Facetorch** is a Python library designed for facial detection and analysis, leveraging the power of deep neural networks. Its primary aim is to curate open-source face analysis models from the community, package them as portable [torch.export](https://pytorch.org/docs/stable/export.html) models, and integrate them into a versatile face analysis toolkit. The library offers the following key features: 1. **Customizable Configuration:** Easily configure your setup using [Hydra](https://hydra.cc/docs/intro/) and its powerful [OmegaConf](https://omegaconf.readthedocs.io/) capabilities. 2. **Reproducible Environments:** Ensure reproducibility with [uv](https://github.com/astral-sh/uv) for fast Python package management, [conda-lock](https://github.com/conda-incubator/conda-lock) for conda-forge dependency management, and [Docker](https://docs.docker.com/get-docker/) for containerization. 3. **Portable Models:** Models are serialized with `torch.export` (`.pt2` format) — no model source code needed at inference time, with dynamic batch support and `torch.compile` compatibility. 4. **Governed Extensibility:** Custom readers, processors, and configurations can be supplied directly. Adding a hosted model to the built-in defaults also requires an immutable manifest entry, validation evidence, provenance, and model-rights approval. 5. **Deterministic Input:** Accepts local paths, tensors, NumPy arrays, PIL images, and bytes through one canonical pipeline. Remote input requires an explicit, bounded `URLReader` configuration. Facetorch provides an efficient, scalable, and user-friendly solution for facial analysis tasks, catering to developers and researchers looking for flexibility and performance. ### Requirements * Python >= 3.11 and < 3.13 * PyTorch 2.6.x through 2.13.x with the matching torchvision minor * Linux x86-64 is the official v1 candidate platform; Windows, macOS, ARM, and Apple MPS are experimental The exact candidate matrix, named CUDA pairs, experimental platforms, and current model-rights gates are documented in [Model compatibility and governance](https://github.com/tomas-gajarsky/facetorch/blob/d73b8b1af1ff0f53dcb480ce2602c11ef908b815/d
Excerpt of 40,774 characters
Read on GitHub
303
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:35220bb3d26d3919, topic:deep-learning, topic:pytorch
matched fp:35220bb3d26d3919, topic:computer-vision