About the PH2 dataset

[lijincan11]

Hello author, I downloaded the ph2 dataset from the connection you provided, and its structure is as follows. My question is, do I need to process it before running the Prepareuph2.py file? If I need to handle it, what are the training and testing sets, respectively?

[wurenkai]

Hi, since the PH2 dataset has a small number of cases, so in our work its mainly treated as an external validation. The PH2 dataset (200 cases) is treated entirely as a test set. Hope my answer will help you.

[lijincan11]

Okay, thank you for your reply. If I want to reproduce, what steps should I take?

  @.***

 

------------------ 原始邮件 ------------------ 发件人: "wurenkai/UltraLight-VM-UNet" @.>; 发送时间: 2024年4月22日(星期一) 晚上11:32 @.>; 抄送: " @.@.>; 主题: Re: [wurenkai/UltraLight-VM-UNet] About the PH2 dataset (Issue #27)

Hi, since the PH2 dataset has a small number of cases, so in our work its mainly treated as an external validation. The PH2 dataset (200 cases) is treated entirely as a test set. Hope my answer will help you.

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

[wurenkai]

Hi, you need to adjust the data format and use 'Prepare_PH2.py '. You can refer to issue 8.