Distributed Arcface Training in Pytorch

This is a deep learning library that makes face recognition efficient, and effective, which can train tens of millions identity on a single server.

Requirements

Install pytorch (torch>=1.6.0), our doc for install.md.
pip install -r requirements.txt.
Download the dataset from https://github.com/deepinsight/insightface/tree/master/recognition/datasets .

How to Training

To train a model, run train.py with the path to the configs:

python train.py configs/webface_mbf

Model Zoo

inference

python3 inference_compare.py --img1 input/sajjad_0.jpg --img2 input/sajjad_1.jpg

Test

We tested many versions of PyTorch. Please create an issue if you are having trouble.

torch 1.6.0
torch 1.7.1
torch 1.8.0
torch 1.9.0

Citation

@inproceedings{deng2019arcface,
  title={Arcface: Additive angular margin loss for deep face recognition},
  author={Deng, Jiankang and Guo, Jia and Xue, Niannan and Zafeiriou, Stefanos},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={4690--4699},
  year={2019}
}
@inproceedings{an2020partical_fc,
  title={Partial FC: Training 10 Million Identities on a Single Machine},
  author={An, Xiang and Zhu, Xuhan and Xiao, Yang and Wu, Lan and Zhang, Ming and Gao, Yuan and Qin, Bin and
  Zhang, Debing and Fu Ying},
  booktitle={Arxiv 2010.05222},
  year={2020}
}

A deep learning library that makes face recognition efficient and effective

Related tags

Overview

Distributed Arcface Training in Pytorch

Requirements

How to Training

Model Zoo

inference

Test

Citation

Owner

Sajjad Aemmi

DeepOBS: A Deep Learning Optimizer Benchmark Suite

Self-supervised learning algorithms provide a way to train Deep Neural Networks in an unsupervised way using contrastive losses

Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning

DSL for matching Python ASTs

Eye-Blink-Counter - Python based Computer Vision project which counts how many time a person blinks

Small little script to scrape, parse and check for active tor nodes. Can be used as proxies.

LETR: Line Segment Detection Using Transformers without Edges

A more easy-to-use implementation of KPConv based on PyTorch.

GPU implementation of $k$-Nearest Neighbors and Shared-Nearest Neighbors

UMT is a unified and flexible framework which can handle different input modality combinations, and output video moment retrieval and/or highlight detection results.

On-device wake word detection powered by deep learning.

Codebase for INVASE: Instance-wise Variable Selection - 2019 ICLR

Pytorch implementation of Learning Rate Dropout.

Implementation of MeMOT - Multi-Object Tracking with Memory - in Pytorch

Codes for "Template-free Prompt Tuning for Few-shot NER".

Byte-based multilingual transformer TTS for low-resource/few-shot language adaptation.

Project ArXiv Citation Network

Notebooks for my "Deep Learning with TensorFlow 2 and Keras" course

HeartRate detector with ArduinoandPython - Use Arduino and Python create a heartrate detector.

SAT: 2D Semantics Assisted Training for 3D Visual Grounding, ICCV 2021 (Oral)