用 VS 搞的一个小游戏...

window 版 SMOKE，省去 linux 下编译 DConv 的 cuda 代码，并增添了 finetune 和 resume 等功能

A more efficient yolov5 with oneflow backend 🎉🎉🎉

matlab findpeaks(signal,'minpeakdistance",d) in C++

Cosine Annealing Warm Booting LR

[ICCVW2021] An Straight Dilated Network with Wavelet for image Deblurring

ntm for pytorch

paper implement

ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection

YOLOv4-MultiTask for Pytorch

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

Implementation for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17.

Add YOLOv3_tiny and data augment(clip, brighten, change saturation)