Michael Du's repositories
tensorflow-face-detection
A mobilenet SSD based face detector, powered by tensorflow object detection api, trained by WIDERFACE dataset.
keras-retinanet
Keras implementation of RetinaNet object detection.
stylegan
StyleGAN
masr
中文语音识别，高识别率预训练模型，支持docker快速安装 Chinese Speech Recognition; Mandarin Automatic Speech Recognition;
SincNet
SincNet is a neural architecture for efficiently processing raw audio samples.
deepface
Deep Learning Models for Face Detection/Recognition/Alignments, implemented in Tensorflow
stylegan2
StyleGAN2 - Official TensorFlow Implementation
Speaker_Verification_GE2E
Tensorflow implementation of generalized end-to-end loss for speaker verification
UDA_pytorch
UDA(Unsupervised Data Augmentation) implemented by pytorch
FaceDetection-DSFD
会导致OOM，可以尝试：
stylegan-encoder
StyleGAN Encoder - converts real images to latent space, forked from https://github.com/Puzer/stylegan-encoder
gitignore
A collection of useful .gitignore templates
lightDSFD
腾讯优图人脸检测模型（Light DSFD)
KD_methods_with_TF
Knowledge distillation methods implemented with Tensorflow (now there are 11 (+1) methods, and will be added more.)
pytorch-yolo2
Convert https://pjreddie.com/darknet/yolo/ into pytorch
x-vector-kaldi-tf
Tensorflow implementation of x-vector topology on top of Kaldi recipe
AdvBox
Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.
fastjson-remote-code-execute-poc
fastjson remote code execute poc 直接用intellij IDEA打开即可 首先编译得到Test.class，然后运行Poc.java
seeprettyface-face_editor
这是一个基于StyleGAN的人脸属性编辑器
mtcnnattack
The first real-world attack on MTCNN face detetction system to date
accessorize-to-a-crime
Code for attacking state-of-the-art face-recognition system from our paper: M. Sharif, S. Bhagavatula, L. Bauer, M. Reiter. "Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition." In Proc. CCS, 2016.
pytorch-CycleGAN-and-pix2pix
Image-to-image translation in PyTorch (e.g., horse2zebra, edges2cats, and more)
cleverhans
An adversarial example library for constructing attacks, building defenses, and benchmarking both
icrawler
A multi-thread crawler framework with many builtin image crawlers provided.
boofuzz
A fork and successor of the Sulley Fuzzing Framework
InsightFace_TF
Insight Face on TensorFlow