保存的.weights模型为啥ｄａｒｋｎｅｔ调用无法检测

[lilei1128]

用ｍｏｄｅｌ中的ｓａｖｅ_darknet_weights（）函数保存的.weights格式模型，为啥在ｄａｒｋｎｅｔ中调用检测不到目标？？？

[wangruo91]

@lilei1128 Hi，我遇到和你一样的问题，你后来解决了么？

[lilei1128]

一个网友说可以把阈值设置的低一点可以检测，你试一下。

------------------ 原始邮件 ------------------ 发件人: "wangruo91"<[email protected]>; 发送时间: 2020年2月10日(星期一) 凌晨0:52 收件人: "Lam1360/YOLOv3-model-pruning"<[email protected]>; 抄送: "LeL"<[email protected]>;"Mention"<[email protected]>; 主题: Re: [Lam1360/YOLOv3-model-pruning] 保存的.weights模型为啥ｄａｒｋｎｅｔ调用无法检测 (#75)

@lilei1128 Hi，我遇到和你一样的问题，你后来解决了么？

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

[wangruo91]

@lilei1128 -thresh设成0.1了都没用，决定直接修改darknet做稀疏训练了。

[Learner-Dan]

You can use darknet to retrain pruned-model

[lilei1128]

You can use darknet to retrain pruned-model

yeah, I thought of this method but didnt try it.