YoloV8改进策略:基于分层注意力的FasterViT,让YoloV8实现性能的飞跃_静静AI学堂的博客-CSDN博客blog.csdn.net/m0_47867638/article/details/131546993
efficientdet,edgenext,efficientformer,efficientnet,eva,fasternet,fastervit,fastvit,flexivit,gcvit,ghostnet,gpvit,hornet,hiera,iformer,inceptionnext,lcnet,levit,maxvit,mobilevit,moganet,nat,nfnets,pvt,swin,tinynet,tinyvit,uniformer,volo,vanillanet,yolor,yolov7,yolov8,yolox,gpt2,llama2, alias ...
这篇文章向大家展示如何使用FasterViT改进YoloV8,我尝试了几种方法,选出了三种效果比较好的方法推荐给大家。测试结果是在我自己标注的数据集上测得,模型选用yolov8l。代码和文章都会上传到百度网盘上,地址详见文章的最后! 官方测试结果 YOLOv8l summary (fused): 268 layers, 43631280 parameters, 0 gradients, ...
Currently 4 types anchors supported, parameter anchors_mode controls which anchor to use, value in ["efficientdet", "anchor_free", "yolor", "yolov8"]. Default None for det_header presets. NOTE: YOLOV8 has a default regression_len=64 for bbox output length. Typically it's 4 for other ...