Image-to-Image Translation in PyTorch

A C++ API of the LFFD with ncnn

face detection

A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......

pytorch implementation of openpose including Hand and Body Pose Estimation.

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

The pretrained models trained on Moments in Time Dataset

TensorRT for Yolov3

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, …

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

🤘 awesome-semantic-segmentation

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

Image augmentation for machine learning experiments.

机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

Official PyTorch implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation

在 oxford hand 数据集上对 YOLOv3 做模型剪枝（network slimming）

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

A Simple and Versatile Framework for Object Detection and Instance Recognition

Open MMLab Detection Toolbox and Benchmark

pytorch 2 caffe

Keras implementation of RetinaNet object detection.

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

🔥Run Linux on the Android with GUI ,Python and AI support. touch-and-drag programming，One-click Installation🔥

[ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang

一款比mini-caffe更快的Forward库，觉得好用请点星啊，400星公布快速人脸检测模型，500星公布106点landmark，600星公布人头检测模型，700星公布人脸检测套餐（六种pnet,两种rnet随意混合使用满足各种速度/精度要求），800星公布更准的106点模型

Face Analysis Project on MXNet

Pytorch implementation of RetinaNet object detection.

🔥improve the accuracy of mobilefacenet(insight face) reached 99.733 in the cfp-ff、 the 99.68+ in lfw,96.71+ in agedb30.🔥

A Keras implementation of YOLOv3 (Tensorflow backend)