search

wuzhe71 / SCRN

Code of Stacked Cross Refinement Network for Edge-Aware Salient Object Detection (ICCV 2019)
77 stars 17 forks source link

How to evaluate the pictures? #1

Open Xjunjiang opened 4 years ago

Xjunjiang commented 4 years ago

Hello, thank you for your work! Can you provide the code for performance evaluation?

wuzhe71 commented 4 years ago

@Xjunjiang my evaluation code is same as amulet (https://github.com/Pchank/caffe-sal)

Xjunjiang commented 4 years ago

Thank you！

------------------ 原始邮件 ------------------ 发件人: "WuZhe"<notifications@github.com>; 发送时间: 2019年11月22日(星期五) 下午3:12 收件人: "wuzhe71/SCRN"<SCRN@noreply.github.com>; 抄送: "JunJiang Xiang"<578744377@qq.com>;"Mention"<mention@noreply.github.com>; 主题: Re: [wuzhe71/SCRN] How to evaluate the pictures? (#1)

@Xjunjiang my evaluation code is same as amulet (https://github.com/Pchank/caffe-sal)

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

Xjunjiang commented 4 years ago

How do you deal with the THUR-15k dataset? Do you only use the annotated dataset on the official website?

wuzhe71 commented 4 years ago

@Xjunjiang yes, only 6232 paired images and labels

StormArcher commented 4 years ago

Thank you！ … ------------------ 原始邮件 ------------------ 发件人: "WuZhe"<notifications@github.com>; 发送时间: 2019年11月22日(星期五) 下午3:12 收件人: "wuzhe71/SCRN"<SCRN@noreply.github.com>; 抄送: "JunJiang Xiang"<578744377@qq.com>;"Mention"<mention@noreply.github.com>; 主题: Re: [wuzhe71/SCRN] How to evaluate the pictures? (#1) @Xjunjiang my evaluation code is same as amulet (https://github.com/Pchank/caffe-sal) — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

do you find the evaluation code in the amulet code ,can you give help ? I just find how to use it ,but don't find the as follow "PR.m, code_pr.m, code_bar.m"

" Testing The testing code is in ./matlab/Amulet_test and ./matlab/UCF_test.

For saliency testing,

(1) Get prediction : test_saliency_dataset.m

(2) Get PR value : PR.m

(3) Plot PR curves: code_pr.m

(4) Plot Bar figures: code_bar.m

(5) Get MAE for each method : getmae.m

Note that we have provided the PR curves in ./PR_curves "