yinxuping Goto Github PK

taobao_seckill

淘宝、天猫半价抢购，抢电视、抢茅台，干死黄牛党

tph-yolov5

transformer-sod

ug2-challenge

An easy algorithm to add synthesis haze to any existing dataset. We use COCO dataset with synthesis haze to train Mask RCNN model and get much better mAP results in object detection in haze challenge than Mask RCNN model trained with original COCO dataset

universalstyletransfer

The source code of NIPS17 'Universal Style Transfer via Feature Transforms'.

visdrone2018-det-toolkit

Object Detection in Images toolkit for VisDrone2019

voc2007_for_yolo_torch

:punch: Prepare VOC format datasets for ultralytics/yolov3 & yolov5

wct2

Software that can perform photorealistic style transfer without the need of any post-processing steps.

wipa-face-super-resolution

Pytorch implementation of WIPA: Super-resolution of very low-resolution face images with a Wavelet Integrated, Identity Preserving, Adversarial Network.

yinxuping.github.io

yolov5_ua_detrac

we train UA_DETRAC dataset by yolov5 to achieve car detection

yolox

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

zid

Pytorch implementation of Zero-Shot Image Dehazing (ZID) (TIP 2020)