ankitvaishnav / look4face

Demo of Face Recognition web service

Look4Face

Demo of Face Recognition web service.

---

Briefly

• The web wrapper is implemented using Django 2.2.
• LFW is used as a main dataset.
• PyTorch for working with neural networks.
• Faiss for ANN search + vector quantization.
• ResNet50 pretrained on MS1M-Arcface.
• For Linux and Mac OS.

---

Easy using with Docker

1. Build image from Dockerfile

$ docker build -t l4fimage .

2. Run container as daemon and expose 8000 port

$ docker run -d --name look4face -p 8000:8000 l4fimage

Installation

If you have CUDA installed, all calculations will be performed on the GPU, otherwise - on the CPU.

1. Install Git-LFS

2. Clone this repository and load LFS objects:

$ git init .
$ git clone https://github.com/sankovalev/Look4Face.git
$ git lfs install
$ git lfs pull

3. Create virtualenv and activate it:

$ virtualenv -p python3 Look4Face
$ cd Look4Face
$ source bin/activate

4. Make sure that you are using python3 & pip3 from virtual environment:

$ which python3
$ which pip3

5. Install all requirements:

$ pip3 install -r requirements.txt

6. Start web server

$ cd Look4Face
$ python3 manage.py runserver

7. Open 127.0.0.1:8000 with browser.

Installation issues

If you receive an error related to Faiss, please visit this link and install additional packages.

Useful links

Repo	Link
face.evoLVe.PyTorch	https://github.com/ZhaoJ9014/face.evoLVe.PyTorch
facenet_pytorch	https://github.com/liorshk/facenet_pytorch
arcface-pytorch	https://github.com/ronghuaiyang/arcface-pytorch
insightface	https://github.com/deepinsight/insightface
sudo docker build -t l4fimage .

How to use with other data

I strongly recommend to use the face.evoLVe.PyTorch repository for train your own models.

1. Put your dataset to Look4Face/datasets with structure:

  Look4Face/datasets/your_db/
                      -> id1/
                          -> 1.jpg
                          -> ...
                      -> id2/
                          -> 1.jpg
                          -> ...
                      -> ...
                          -> ...
                          -> ...

and set variable in Look4Face/Look4Face/settings.py:

DATASET_FOLDER = 'your_db'

2. Similarly, put your Faiss index and meta information for labels (dict with pairs id:PersonName) to the same folder, set variables:

DATASET_INDEX = 'your_index.bin'
DATASET_LABELS = 'your_labels.pkl'

3. Update Backbone.pth if you need:

  Look4Face/backbone/
                     -> your_backbone.pth

and set variable in Look4Face/Look4Face/settings.py:

BACKBONE_FILE = 'your_backbone.pth'

Todos

• Write notification if there are no faces on photo.
• Write tutorial about using own dataset.

License

MIT