ImageAI v2.03 各种模型介绍

对象检测objectdetection

  1. RetinaNet (Size = 145 mb, high performance and accuracy, with longer detection time) 

    YOLOv3 (Size = 237 mb, moderate performance and accuracy, with a moderate detection time) 

    TinyYOLOv3 (Size = 34 mb, optimized for speed and moderate performance, with fast detection time) 

图像预测 Prediction

  1. SqueezeNet (Size = 4.82 mb, fastest prediction time and moderate accuracy) 
    ResNet50 by Microsoft Research (Size = 98 mb, fast prediction time and high accuracy) 
    InceptionV3 by Google Brain team (Size = 91.6 mb, slow prediction time and higher accuracy) 
    DenseNet121 by Facebook AI Research (Size = 31.6 mb, slower prediction time and highest accuracy) 

转载于:https://my.oschina.net/u/4158242/blog/3069705

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值