dice和f1化简之后公式似乎一样

[pipixiaipip]

老师您好，根据您提供的代码，dice和f1化简之后都等于： 2TP/（2TP+FP+FN），可是在您的论文中为什么会得出不一样的结果呢，应该是一样的啊。还请老师为我答疑解惑，谢谢！

[haifangong]

Thank you very much for pointing this out. We are very sorry that there exist a type error in the table, the F1-score metric should be the precision metric. We will update this information in the furture.

[pipixiaipip]

谢谢老师的回复，应该是dice那一栏为precision。

[wangx0530]

你好，请问你做过这篇文章的复现吗？能不能跟你交流一下

谢谢老师的回复，应该是dice那一栏为precision。

[pipixiaipip]

最近在尝试复现，可以一起交流啊。

你好，请问你把这篇文章复现了吗？能不能交流一下

[1254bhj]

ValueError: too many values to unpack (expected 2).

hello,i wanna learn how did yuou slove this problem

[pipixiaipip]

ValueError: too many values to unpack (expected 2).

hello,i wanna learn how did yuou slove this problem

Change return nodule, thyroid, scale to return nodule

[1254bhj]

i do that like you say "Change return nodule, thyroid, scale to return nodule",but the error is also exist,So I don't think that's the problem

周鹏 @.***

 

------------------ 原始邮件 ------------------ 发件人: "haifangong/TRFE-Net-for-thyroid-nodule-segmentation" @.>; 发送时间: 2024年1月1日(星期一) 晚上10:01 @.>; @.@.>; 主题: Re: [haifangong/TRFE-Net-for-thyroid-nodule-segmentation] dice和f1化简之后公式似乎一样 (Issue #7)

ValueError: too many values to unpack (expected 2).

hello,i wanna learn how did yuou slove this problem

Change return nodule, thyroid, scale to return nodule

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

[pipixiaipip]

i do that like you say "Change return nodule, thyroid, scale to return nodule",but the error is also exist,So I don't think that's the problem 周鹏 @.***   … ------------------ 原始邮件 ------------------ 发件人: "haifangong/TRFE-Net-for-thyroid-nodule-segmentation" @.>; 发送时间: 2024年1月1日(星期一) 晚上10:01 @.>; @.@.>; 主题: Re: [haifangong/TRFE-Net-for-thyroid-nodule-segmentation] dice和f1化简之后公式似乎一样 (Issue #7) ValueError: too many values to unpack (expected 2). hello,i wanna learn how did yuou slove this problem Change return nodule, thyroid, scale to return nodule — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

那就不知道啦

[1254bhj]

 i revise the error "ValueError: too many values to unpack (expected 2)"; but there is a new error:

i printed the trainloader as shown above, what does "scale =nodules['scale'].cuda()" mean? ,i cant find the scale in dataloader?

 

周鹏 @.***

 

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2024年1月11日(星期四) 晚上8:19 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [haifangong/TRFE-Net-for-thyroid-nodule-segmentation] dice和f1化简之后公式似乎一样 (Issue #7)

i do that like you say "Change return nodule, thyroid, scale to return nodule",but the error is also exist,So I don't think that's the problem 周鹏 @.***   … ------------------ 原始邮件 ------------------ 发件人: "haifangong/TRFE-Net-for-thyroid-nodule-segmentation" @.>; 发送时间: 2024年1月1日(星期一) 晚上10:01 @.>; @.@.>; 主题: Re: [haifangong/TRFE-Net-for-thyroid-nodule-segmentation] dice和f1化简之后公式似乎一样 (Issue #7) ValueError: too many values to unpack (expected 2). hello,i wanna learn how did yuou slove this problem Change return nodule, thyroid, scale to return nodule — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

那就不知道啦

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>