Pinned Repositories
A-Light-and-Fast-Face-Detector-for-Edge-Devices
A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......
advanced_lane_detection
Advanced lane detection using computer vision
AdvancedEAST
AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on EAST, and the significant improvement was also made, which make long text predictions more accurate.
Anime-InPainting
An application tool of edge-connect, which can do anime inpainting and drawing. 动漫人物图片自动修复，去马赛克，填补，去瑕疵
deep_learning
deep learning of my repository
dense_flow
EDSR-Tensorflow
Tensorflow implementation of Enhanced Deep Residual Networks for Single Image Super-Resolution
Human-Falling-Detect-Tracks
AlphaPose + ST-GCN + SORT.
reid-mgn
Reproduction of paper: Learning Discriminative Features with Multiple Granularities for Person Re-Identification
SMAD-on-fire
Based on the detection of fire in videos, binocular stereo matching technology is used to determine the location of fire sources .
Gavin666Github's Repositories
Gavin666Github/ASTGCN
Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting (ASTGCN) AAAI 2019
Gavin666Github/BASNet
Code for CVPR 2019 paper. BASNet: Boundary-Aware Salient Object Detection
Gavin666Github/CBIR
🏞 A content-based image retrieval (CBIR) system
Gavin666Github/deep-high-resolution-net.pytorch
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
Gavin666Github/DEye
Keep an Eye on Defects Inspection.
Gavin666Github/Dlib_face_recognition_from_camera
Detect and recognize the faces from camera / 调用摄像头进行人脸识别，支持多张人脸同时识别
Gavin666Github/DSC
CVPR 2018 (Oral) & TPAMI 2019
Gavin666Github/EDVR
Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks
Gavin666Github/fisheye
fisheye image calibration
Gavin666Github/Image-processing-algorithm
paper implement
Gavin666Github/Keras-Semantic-Segmentation
Keras-Semantic-Segmentation
Gavin666Github/Lightweight-Segmentation
Lightweight models for real-time semantic segmentation(include mobilenetv1-v3, shufflenetv1-v2, igcv3, efficientnet).
Gavin666Github/LPRNet_Pytorch
Pytorch Implementation For LPRNet, A High Performance And Lightweight License Plate Recognition Framework.
Gavin666Github/openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Gavin666Github/pysot
SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.
Gavin666Github/PyTorch-YOLOv3
Minimal PyTorch implementation of YOLOv3
Gavin666Github/stereo-vision-1
A multiple computer vision and machine learning algorithms development/integration
Gavin666Github/Stereovision
Use OpenCV and PsEye cameras to track object position, velocity
Gavin666Github/super-resolution
Keras-based implementation of WDSR, EDSR and SRGAN for single image super-resolution
Gavin666Github/tf-pose-estimation
Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.
Gavin666Github/training
🐝 Custom Object Detection and Classification Training
Gavin666Github/Transferable-Interactiveness-Network
Codes for Transferable Interactiveness Knowledge for Human-Object Interaction Detection. (CVPR 2019)
Gavin666Github/unet
unet for image segmentation
Gavin666Github/unofficial-implement-of-openpose
Simple Implement of Openpose use Tensorflow代码贼简单，tensorboard很全
Gavin666Github/Video-summarization
视频摘要
Gavin666Github/videopose
3D pose estimation for wild videos， embed 2d keypoints detector like hrnet alphapose and openpose
Gavin666Github/VideoPose3D
Efficient 3D human pose estimation in video using 2D keypoint trajectories
Gavin666Github/voxelmorph
Unsupervised Learning for Image Registration
Gavin666Github/vsrnet_pytorch
PyTorch implementation of paper "Video super-resolution with convolutional neural networks"
Gavin666Github/YOLOv3-model-pruning
对 YOLOv3 做模型剪枝，在 oxford hand 数据集上模型的参数量减少 80% ，FLOPs 降低 70%，Infer 的速度可以达到原来的 200%，mAP 基本保持不变