guanfuchen / facedet Goto Github PK

实现常用基于深度学习的人脸检测算法华为媒体研究院图文Caption、OCR识别、图视文多模态理解与生成相关方向工作或实习欢迎咨询 15757172165 https://guanfuchen.github.io/media/hw_zhaopin_20220724_tiny.jpg

Python 100.00%

facedetection convolutional-neural-networks pytorch deep-learning faceboxes widerface fddb face-alignment

facedet's Introduction

facedet

face detection algorithms

公告

避免大家花费时间去折腾，说明如下，目前该仓库主要还是将faceboxes阅读修改，基本跑通但是性能等还未系统测试，大家可以直接参考作者实现。下一步将最近阅读的人脸检测框架尝试统一实现并能获得较好的性能，整体实现思路尝试我写的语义分割框架semseg的完善思路，有想法的可以一起来学习实现。

Announcement

Avoid everyone spending time to toss, as explained below, the current warehouse is still mainly faceboxes read and modify, basically run through but performance has not been systematically tested, you can directly refer to The author realizes that the next step is to try to implement the face detection framework recently and achieve better performance. Try the perfect idea of the semantic segmentation framework semseg, and have ideas. Can be learned together to achieve.

概述

这个仓库旨在实现常用的人脸检测算法，主要参考如下：

faceboxes 使用multi scale one shot的CNN网络实现人脸检测。
face_classification，实时的人脸检测（OpenCV）和分类（情感和性别）。
Face-Resources，其中有相关人脸模型和数据集资源。
awesome-face，整理过的人脸检测论文和数据集。
mxnet-face，常用的face相关论文的mxnet实现。

人脸识别

MobileFace
facenet_caffe
Person_reID_baseline_pytorch，使用pytorch实现的经典reid模型。
deep-person-reid
Face Alignment in Full Pose Range: A 3D Total Solution

行人检测

Is Faster R-CNN Doing Well for Pedestrian Detection?
CityPersons: A Diverse Dataset for Pedestrian Detection
Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting，行人检测

网络

FaceBoxes，实现问题参考facebox_understanding，已实现
CascadeCNN，实现问题参考cascadeface_understanding，未实现
MTCNN，实现问题参考mtcnn_understanding，未实现。
S3FD，实现问题可参考s3fd_understanding，未实现。
Faster RCNN，参考技术报告Face Detection with the Faster R-CNN，和对应源代码face-py-faster-rcnn。
SSH，实现代码可参考SSH。

数据

人脸检测数据集可参考Face Detection Dataset 其中主要有WIDER FACE，IJBA-A，MALF，FDDB和AFW数据集。

详细数据集相关实现问题参考facedet_dataset_understanding

WIDER FACE，实现问题参考wider_face_understanding
FDDB，实现问题可参考fddb_understanding
AFLW，实现问题可参考aflw_understanding
CelebA，大尺度CelebFaces属性，实现问题可参考celeba_understanding
IMDb-Face，IMBb人脸噪声数据，可查看IMDb-Face

用法

可视化

visdom 开发相关问题

# 在tmux或者另一个终端中开启可视化服务器visdom
python -m visdom.server
# 然后在浏览器中查看127.0.0.1:9097

训练

# 训练模型
python train.py

校验

# 校验模型
python validate.py

测试

# 测试模型
python test.py

demo

# 读取摄像头实时检测人脸
python demo.py

依赖

pytorch
...

facedet's People

Contributors

Stargazers

Watchers

facedet's Issues

秋招都变成第二批了，还不如花些时间撸撸代码

有没有人有兴趣一起实现这些常用模型～～

model for android

hello，
thanks for your sharing，can you convert the model to android??

Robust Face Detection via Learning Small Faces on Hard Images

related paper

摘要
Recent anchor-based deep face detectors have achieved promising performance, but they are still struggling to detect hard faces, such as small, blurred and partially occluded faces. A reason is that they treat all images and faces equally, without putting more effort on hard ones; however, many training images only contain easy faces, which are less helpful to achieve better performance on hard images. In this paper, we propose that the robustness of a face detector against hard faces can be improved by learning small faces on hard images. Our intuitions are (1) hard images are the images which contain at least one hard face, thus they facilitate training robust face detectors; (2) most hard faces are small faces and other types of hard faces can be easily converted to small faces by shrinking. We build an anchor-based deep face detector, which only output a single feature map with small anchors, to specifically learn small faces and train it by a novel hard image mining strategy. Extensive experiments have been conducted on WIDER FACE, FDDB, Pascal Faces, and AFW datasets to show the effectiveness of our method. Our method achieves APs of 95.7, 94.9 and 89.7 on easy, medium and hard WIDER FACE val dataset respectively, which surpass the previous state-of-the-arts, especially on the hard subset. Code and model are available at https://github.com/bairdzhang/smallhardface.

Pairwise Relational Networks using Local Appearance Features for Face Recognition

related paper

摘要
We propose a new face recognition method, called a pairwise relational network (PRN), which takes local appearance features around landmark points on the feature map, and captures unique pairwise relations with the same identity and discriminative pairwise relations between different identities. The PRN aims to determine facial part-relational structure from local appearance feature pairs. Because meaningful pairwise relations should be identity dependent, we add a face identity state feature, which obtains from the long short-term memory (LSTM) units network with the sequential local appearance features. To further improve accuracy, we combined the global appearance features with the pairwise relational feature. Experimental results on the LFW show that the PRN achieved 99.76% accuracy. On the YTF, PRN achieved the state-of-the-art accuracy (96.3%). The PRN also achieved comparable results to the state-of-the-art for both face verification and face identification tasks on the IJB-A and IJB-B. This work is already published on ECCV 2018.

摘要
Whilst recent face-recognition (FR) techniques have made significant progress on recognising constrained high-resolution web images, the same cannot be said on natively unconstrained low-resolution images at large scales. In this work, we examine systematically this under-studied FR problem, and introduce a novel Complement SuperResolution and Identity (CSRI) joint deep learning method with a unified end-to-end network architecture. We further construct a new large-scale dataset TinyFace of native unconstrained low-resolution face images from selected public datasets, because none benchmark of this nature exists in the literature. With extensive experiments we show there is a significant gap between the reported FR performances on popular benchmarks and the results on TinyFace, and the advantages of the proposed CSRI over a variety of state-of-the-art FR and super-resolution deep models on solving this largely ignored FR scenario. The TinyFace dataset is released publicly at: https://qmul-tinyface.github.io/.

Quantized Densely Connected U-Nets for Efficient Landmark Localization

related paper

摘要
In this paper, we propose quantized densely connected U-Nets for efficient visual landmark localization. The idea is that features of the same semantic meanings are globally reused across the stacked U-Nets. This dense connectivity largely improves the information flow, yielding improved localization accuracy. However, a vanilla dense design would suffer from critical efficiency issue in both training and testing. To solve this problem, we first propose order-K dense connectivity to trim off long-distance shortcuts; then, we use a memory-efficient implementation to significantly boost the training efficiency and investigate an iterative refinement that may slice the model size in half. Finally, to reduce the memory consumption and high precision operations both in training and testing, we further quantize weights, inputs, and gradients of our localization network to low bit-width numbers. We validate our approach in two tasks: human pose estimation and face alignment. The results show that our approach achieves state-of-the-art localization accuracy, but using ∼70% fewer parameters, ∼98% less model size and saving ∼75% training memory compared with other benchmark localizers. The code is available at https://github.com/zhiqiangdon/CU-Net.

guanfuchen / facedet Goto Github PK

facedet's Introduction

facedet

公告

Announcement

概述

人脸识别

行人检测

网络

数据

用法

依赖

facedet's People

Contributors

Stargazers

Watchers

Forkers

facedet's Issues

Recommend Projects

Recommend Topics

Recommend Org