azuredsky

Efficient_ImageNet_Classification

An efficient implementation for ImageNet classification

face_mask_tengine_lite

1MB-License-Plate-Detection-With-4-Landmarks

rt_gene

RT-GENE: Real-Time Eye Gaze and Blink Estimation in Natural Environments

AndroidLibyuvImageUtils

A image processing library on Android, base on the libyuv.

AVSE

BAMSE

Bone/Air conducted speech signal enhancement exploiting multi-modal framework

BiSeNet

Add bisenetv2. My implementation of BiSeNet

DALI

A library containing both highly optimized building blocks and an execution engine for data pre-processing in deep learning applications

deep-sdm

deep-sdm is appied for face landmark.

ECANet

Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

FaceLandmark_PFLD_UltraLight

Focal-Loss-Pytorch

全中文注释.(The loss function of retinanet based on pytorch).(You can use it on one-stage detection task or classifical task, to solve data imbalance influence).用于one-stage目标检测算法,提升检测效果.你也可以在分类任务中使用该损失函数,解决数据不平衡问题.

KWS-Net

Seeing Wake Words: Audio-visual Keyword Spotting

libfacedetection.train

The training program for libfacedetection for face detection and 5-landmark detection.

Lip2Wav

This is the repository containing codes for our CVPR, 2020 paper titled "Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis"

LSTR

This is an official repository of End-to-end Lane Shape Prediction with Transformers.

mobile-yolov5-pruning-distillation

mobilev2-yolov5s剪枝、蒸馏，支持ncnn，tensorRT部署。ultra-light but better performence！

pytorch-distributed

A quickstart and benchmark for pytorch distributed training.

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2/V1, MNASNet, Single-Path NAS, FBNet, and more

pytorch_classification

利用pytorch实现图像分类的一个完整的代码，训练，预测，TTA，模型融合，模型部署，cnn提取特征，svm或者随机森林等进行分类，模型蒸馏，一个完整的代码

ScaledYOLOv4

:fire::fire::fire: Scaled-YOLOv4训练自己的数据集详细教程PDF，关于paper解读请联系小编获取PDF文档

Segmentation-Pytorch

Semantic Segmentation in Pytorch.Network include UNet、ENet、ESPNet、ESPNet_v2、ERFNet、DABNet、BiSeNetV2、PSPNet、DeeplabV3Plus

Smart_Construction

Head Person Helmet Detection on Construction Sites，基于目标检测工地安全帽和禁入危险区域识别系统，🚀😆附 YOLOv5 训练自己的数据集超详细教程！！！😆🚀

syncnet_python

Out of time: automated lip sync in the wild

Tengine

Tengine is a lite, high performance, modular inference engine for embedded device

tensorflow-mtcnn

C++ and python Inference only for MTCNN face detector on Tensorflow. Based on davidsandberg's facenet project:

tensorRT

TensorRT-7 Network Lib 包括常用目标检测、关键点检测、人脸检测、OCR等 可训练自己数据

tensorrt-yolov5

a yolov5 implementation using tensorrt, running on Jetson devices.

Wav2Lip

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020.