Deep Face Recognition in PyTorch

Overview

Face Recognition in PyTorch

License Build Status

By Alexey Gruzdev and Vladislav Sovrasov

Introduction

A repository for different experimental Face Recognition models such as CosFace, ArcFace, SphereFace, SV-Softmax, etc.

Contents

  1. Installation
  2. Preparation
  3. Train/Eval
  4. Models
  5. Face Recognition Demo

Installation

  1. Create and activate virtual python environment
bash init_venv.sh
. venv/bin/activate

Preparation

  1. For Face Recognition training you should download VGGFace2 data. We will refer to this folder as $VGGFace2_ROOT.
  2. For Face Recognition evaluation you need to download LFW data and LFW landmarks. Place everything in one folder, which will be $LFW_ROOT.

Train/Eval

  1. Go to $FR_ROOT folder
cd $FR_ROOT/
  1. To start training FR model:
python train.py --train_data_root $VGGFace2_ROOT/train/ --train_list $VGGFace2_ROOT/meta/train_list.txt
--train_landmarks  $VGGFace2_ROOT/bb_landmark/ --val_data_root  $LFW_ROOT/lfw/ --val_list $LFW_ROOT/pairs.txt  
--val_landmarks $LFW_ROOT/lfw_landmark.txt --train_batch_size 200  --snap_prefix mobilenet_256 --lr 0.35
--embed_size 256 --model mobilenet --device 1
  1. To evaluate FR snapshot (let's say we have MobileNet with 256 embedding size trained for 300k):
 python evaluate_lfw.py --val_data_root $LFW_ROOT/lfw/ --val_list $LFW_ROOT/pairs.txt
 --val_landmarks $LFW_ROOT/lfw_landmark.txt --snap /path/to/snapshot/mobilenet_256_300000.pt --model mobilenet --embed_size 256

Configuration files

Besides passing all the required parameters via command line, the training script allows to read them from a yaml configuration file. Each line of such file should contain a valid description of one parameter in the yaml fromat. Example:

#optimizer parameters
lr: 0.4
train_batch_size: 256
#loss options
margin_type: cos
s: 30
m: 0.35
#model parameters
model: mobilenet
embed_size: 256
#misc
snap_prefix: MobileFaceNet
devices: [0, 1]
#datasets
train_dataset: vgg
train_data_root: $VGGFace2_ROOT/train/
#... and so on

Path to the config file can be passed to the training script via command line. In case if any other arguments were passed before the config, they will be overwritten.

python train.py -m 0.35 @./my_config.yml #here m can be overwritten with the value from my_config.yml

Models

  1. You can download pretrained model from fileshare as well - https://download.01.org/openvinotoolkit/open_model_zoo/training_toolbox_pytorch/models/fr/Mobilenet_se_focal_121000.pt
cd $FR_ROOT
python evaluate_lfw.py --val_data_root $LFW_ROOT/lfw/ --val_list $LFW_ROOT/pairs.txt --val_landmarks $LFW_ROOT/lfw_landmark.txt
--snap /path/to/snapshot/Mobilenet_se_focal_121000.pt --model mobilenet --embed_size 256
  1. You should get the following output:
I1114 09:33:37.846870 10544 evaluate_lfw.py:242] Accuracy/Val_same_accuracy mean: 0.9923
I1114 09:33:37.847019 10544 evaluate_lfw.py:243] Accuracy/Val_diff_accuracy mean: 0.9970
I1114 09:33:37.847069 10544 evaluate_lfw.py:244] Accuracy/Val_accuracy mean: 0.9947
I1114 09:33:37.847179 10544 evaluate_lfw.py:245] Accuracy/Val_accuracy std dev: 0.0035
I1114 09:33:37.847229 10544 evaluate_lfw.py:246] AUC: 0.9995
I1114 09:33:37.847305 10544 evaluate_lfw.py:247] Estimated threshold: 0.7241

Demo

  1. For setting up demo, please go to Face Recognition demo with OpenVINO Toolkit
Owner
Alexey Gruzdev
Going Deeper with Deep Learning
Alexey Gruzdev
GAN-based 3D human pose estimation model for 3DV'17 paper

Tensorflow implementation for 3DV 2017 conference paper "Adversarially Parameterized Optimization for 3D Human Pose Estimation". @inproceedings{jack20

Dominic Jack 15 Feb 27, 2021
A series of convenience functions to make basic image processing operations such as translation, rotation, resizing, skeletonization, and displaying Matplotlib images easier with OpenCV and Python.

imutils A series of convenience functions to make basic image processing functions such as translation, rotation, resizing, skeletonization, and displ

Adrian Rosebrock 4.3k Jan 08, 2023
Dilated Convolution with Learnable Spacings PyTorch

Dilated-Convolution-with-Learnable-Spacings-PyTorch Ismail Khalfaoui Hassani Dilated Convolution with Learnable Spacings (abbreviated to DCLS) is a no

15 Dec 09, 2022
[ICLR 2021] HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark

HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark Accepted as a spotlight paper at ICLR 2021. Table of content File structure Prerequi

72 Jan 03, 2023
To propose and implement a multi-class classification approach to disaster assessment from the given data set of post-earthquake satellite imagery.

To propose and implement a multi-class classification approach to disaster assessment from the given data set of post-earthquake satellite imagery.

Kunal Wadhwa 2 Jan 05, 2022
HashNeRF-pytorch - Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives

HashNeRF-pytorch Instant-NGP recently introduced a Multi-resolution Hash Encodin

Yash Sanjay Bhalgat 616 Jan 06, 2023
NFT-Price-Prediction-CNN - Using visual feature extraction, prices of NFTs are predicted via CNN (Alexnet and Resnet) architectures.

NFT-Price-Prediction-CNN - Using visual feature extraction, prices of NFTs are predicted via CNN (Alexnet and Resnet) architectures.

5 Nov 03, 2022
PyTorch implementation of Self-supervised Contrastive Regularization for DG (SelfReg)

SelfReg PyTorch official implementation of Self-supervised Contrastive Regularization for Domain Generalization (SelfReg, https://arxiv.org/abs/2104.0

64 Dec 16, 2022
This repository contains the segmentation user interface from the OpenSurfaces project, extracted as a lightweight tool

OpenSurfaces Segmentation UI This repository contains the segmentation user interface from the OpenSurfaces project, extracted as a lightweight tool.

Sean Bell 66 Jul 11, 2022
IMBENS: class-imbalanced ensemble learning in Python.

IMBENS: class-imbalanced ensemble learning in Python. Links: [Documentation] [Gallery] [PyPI] [Changelog] [Source] [Download] [知乎/Zhihu] [中文README] [a

Zhining Liu 176 Jan 04, 2023
OpenMMLab Detection Toolbox and Benchmark

MMDetection is an open source object detection toolbox based on PyTorch. It is a part of the OpenMMLab project.

OpenMMLab 22.5k Jan 05, 2023
From Canonical Correlation Analysis to Self-supervised Graph Neural Networks

Code for CCA-SSG model proposed in the NeurIPS 2021 paper From Canonical Correlation Analysis to Self-supervised Graph Neural Networks.

Hengrui Zhang 44 Nov 27, 2022
banditml is a lightweight contextual bandit & reinforcement learning library designed to be used in production Python services.

banditml is a lightweight contextual bandit & reinforcement learning library designed to be used in production Python services. This library is developed by Bandit ML and ex-authors of Facebook's app

Bandit ML 51 Dec 22, 2022
This repository is for Competition for ML_data class

This repository is for Competition for ML_data class. Based on mmsegmentatoin,mainly using swin transformer to completed the competition.

jianlong 2 Oct 23, 2022
Prototype-based Incremental Few-Shot Semantic Segmentation

Prototype-based Incremental Few-Shot Semantic Segmentation Fabio Cermelli, Massimiliano Mancini, Yongqin Xian, Zeynep Akata, Barbara Caputo -- BMVC 20

Fabio Cermelli 21 Dec 29, 2022
A containerized REST API around OpenAI's CLIP model.

OpenAI's CLIP — REST API This is a container wrapping OpenAI's CLIP model in a RESTful interface. Running the container locally First, build the conta

Santiago Valdarrama 48 Nov 06, 2022
The undersampled DWI image using Slice-Interleaved Diffusion Encoding (SIDE) method can be reconstructed by the UNet network.

UNet-SIDE The undersampled DWI image using Slice-Interleaved Diffusion Encoding (SIDE) method can be reconstructed by the UNet network. For Super Reso

TIANTIAN XU 1 Jan 13, 2022
Language-Agnostic Website Embedding and Classification

Homepage2Vec Language-Agnostic Website Embedding and Classification based on Curlie labels https://arxiv.org/pdf/2201.03677.pdf Homepage2Vec is a pre-

25 Dec 27, 2022
Simple tutorials on Pytorch DDP training

pytorch-distributed-training Distribute Dataparallel (DDP) Training on Pytorch Features Easy to study DDP training You can directly copy this code for

Ren Tianhe 188 Jan 06, 2023
NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size

NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size Xuanyi Dong, Lu Liu, Katarzyna Musial, Bogdan Gabrys in IEEE Transactions o

D-X-Y 137 Dec 20, 2022