🔥Deep Learning for Face Anti-Spoofing

A collection of 100 Deep Learning images and visualizations

A paper list of object detection using deep learning.

该工作由电子科技大学陈昂、刘俊凯、夏子寒同学完成。我们提出可以使用深度学习的方案对中国车牌进行检测和识别。我们提出使用YOLOv3网络进行车牌检测，然后创新性地对检测后的车牌使用空间变换网络STN加以校正，最后使用LPRNet网络进行车牌的字符与数字识别。目前实测结果，在老师提供的45张数据集上，我们的YOLOv3网络检测准确率（IOU）达到98.2%，深度学习级联网络识别准确率为95.6%…

yolo3+ocr

[ECCV 2018] CCPD: a diverse and well-annotated dataset for license plate detection and recognition

A curated list of resources for text detection/recognition (optical character recognition ) with deep learning methods.

Datasets, Transforms and Models specific to Computer Vision

Generate the fake Chinese license plate images for detection & recognition

TF2.0 port for Augmix paper

Artificial Intelligence

Literature survey, paper reviews, experimental setups and a collection of implementations for baselines methods for predictive uncertainty estimation in deep learning models.

pytorch handbook是一本开源的书籍，目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门，其中包含的Pytorch教程全部通过测试保证可以成功运行

Awesome resources of yousan.ai(closely related to deep learning).

Codes for Regularized Fine-grained Meta Face Anti-spoofing in AAAI 2020

A caffe implementation of MobileNet-YOLO detection network

Python package to corrupt arbitrary images.

Awesome Object Detection based on handong1587 github: https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html

Pedestrian Detection Papers

(ICCV 2019) Uncertainty-aware Face Representation and Recognition

Face Analysis Project on MXNet

Retinaface caffe with mnetv2 0.25(and many more)

[CVPR19] FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation from a Single Image

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Encoder and decoder with attention model for chinese_ocr in Pytorch 1.0

Caffe Implementation of MobileNets V3

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

Object detection, 3D detection, and pose estimation using center point detection:

Single Image Reflection Separation with Perceptual Losses