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.
GIPHY's Open-Source Celebrity Detection Deep Learning Model
| Date | Stars |
|---|---|
| 2026-07-31 | 692 |
| 2026-08-01 | 692 |
| 2026-08-06 | 692 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# GIPHY Celebrity Detector
GIPHY's Open Source Celebrity Detection Deep Learning Model and Code
## About
GIPHY is proud to release our custom machine learning model that is able to discern over 2,300 celebrity faces with 98% accuracy. The model was trained to identify the most popular celebs on GIPHY, and can identify and make predictions for multiple faces across a sequence of images, like GIFs and videos.
This project was developed by the GIPHY R&D team with the goal to build a deep learning model that could annotate our most popular content as well as, or hopefully better than, similar models offered by major tech companies. We’re extremely proud of our results, and have released this model and training code to the public in hopes that others might build off our work, integrate the model into their own projects, or perhaps learn from our approach.
Read more about the project on the [GIPHY engineering blog](https://engineering.giphy.com/giphys-ai-can-identify-lil-yachty-can-yours).
We’ve provided a [list of all celebrities](https://github.com/Giphy/celeb-detection-oss/blob/master/examples/resources/face_recognition/labels.csv) available with the model.
Thank you!
The GIPHY R&D Team
Nick Hasty [@jnhasty](https://github.com/jnhasty), Ihor Kroosh [@tilast](https://github.com/tilast), Dmitry Voitekh [@dvoitekh](https://github.com/dvoitekh), Dmytro Korduban [@dkorduban](https://github.com/dkorduban)
## Try it out!
Follow the instructions in the [examples directory](./examples) to download the model and test it on your own GIFs and videos.
## Prerequisites
1. Python 3.6 or higher
2. For Linux: libsm, libxext, libxrender
## Training & Transfer Learning Experimentation Pipeline
Preliminary steps:
1. Create a work directory to store results of experiments (it's not mandatory to locate this directory within the project). Example is provided [here](./workdir/).
2. Inside a work directory create an experiment directory. It's name must match the name of the related experiment python file (e.g. [example_experiment](./workdir/example_experiment/) directory for [example_experiment.py](./experiments/example_experiment.py) file).
2. Create a directory `face_recognition` inside work directory, which must contain weights for MTCNN model (3 files with names `det1.npy`, `det2.npy`, and `det3.npy` that can be copied from [Giphy pretrained resources archive](https://s3.amazonaws.com/giphy-public/models/celeb-detection/resources.tar.gz)).
3. Create a file `labels.csv` inside the experiment directory. It must be of the following structure (see example [here](examples/resources/face_recognition/labels.csv)):
```
Label,Index
Person1,0
Person2,1
Person3,3
...
```
4. Create directory `raw_dataset` inside the experiment directory. It's a dataset of uncropped images. It must be of the following structure:
```
- raw_dataset
- Person1
image1.jpg
image2.jpg
image3.jpg
...
+ Person2
+ Person3
...
```
So the overall structure of the work directory is as follows:
```
- workdir
- example_experiment
- raw_dataset
- Person1
image1.jpg
image2.jpg
image3.jpg
...
+ Person2
+ Person3
...
labels.csv
- face_detection
det1.npy
det2.npy
det3.npy
```
After that, you need to choose where you going to run training: on CPU or on GPU. According to this decision you need to change `requirements_cpu.txt` to `requirements_gpu.txt` in `setup.py`, or leave it as is. Also, please, mind changing `tensorflow` version if necessary.
### Using Python 3.6 Package
1. Create a virtual environment to localize dependencies (optional):
https://virtualenv.pypa.io/en/latest/
```
pip install --upgrade virtualenv
virtualenv -p python3 venv
activate
source ./venv/bin/activate
```
2. Install the package:
```
pip install -e .
```
3. Create your experiment Excerpt of 5,488 characters
Read on GitHub
6
5
4
Christian Clauss · Christian Clauss · Switzerland
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8218f285fd0f5ed1, llm:description: "GIPHY's Open-Source Celebrity Detection Deep Learning Model" (repo description)
matched fp:8218f285fd0f5ed1, llm:description: "GIPHY's Open-Source Celebrity Detection Deep Learning Model" (repo description)
matched fp:8218f285fd0f5ed1, llm:description: "GIPHY's Open-Source Celebrity Detection Deep Learning Model" (repo description)