How do we use the inference.py with custom movieclip but with no salient map

[nelsontseng0704]

Hi Roudgers,

Is there any possible we can get salient map without any label map(png) when running inference.py. I did run inference.py by setting to ViSal and looks like the model still needs groud-truth salient map png to run the inference mode. Where I can modify to run inference.py with movieclip(JPGs) without salient map (png)

Many thanks,

[Roudgers]

Hi,   For your question, we have considered putting GT into ‘dataset’ at the beginning. You can download the test datasets through the link given in our project (including ViSal, and other test datasets).

  Best wishes.

------------------ 原始邮件 ------------------ 发件人: "Roudgers/DCFNet" @.>; 发送时间: 2021年8月27日(星期五) 凌晨0:22 @.>; @.***>; 主题: [Roudgers/DCFNet] How do we use the inference.py with custom movieclip but with no salient map (#2)

Hi Roudgers,

Is there any possible we can get salient map without any label map(png) when running inference.py. I did run inference.py by setting to ViSal and looks like the model still needs groud-truth salient map png to run the inference mode. Where I can modify to run inference.py with movieclip(JPGs) without salient map (png)

Many thanks,

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.