how to inference model use other image? about deepfashion_try_on

[LZQhardworker]

We will release train code next week, and also rearrange the test code for easy access. 获取 Outlook for iOS<https://aka.ms/o0ukef>

…

________________________________ 发件人: Qingyun Wang <[email protected]> 发送时间: Wednesday, June 3, 2020 12:29:06 AM 收件人: switchablenorms/DeepFashion_Try_On <[email protected]> 抄送: Yang; Han <[email protected]>; Comment <[email protected]> 主题: Re: [switchablenorms/DeepFashion_Try_On] how to inference model use other image? (#4) Thanks for clarifying, I think I understand the code now! The generated image will store in the 'sample' folder. Would you share some more information on data-preprocessing? I image that the labels are obtained from some segmentation model, the pose are obtained from openpose, is that right? What is the 'edge' variable? ― You are receiving this because you commented. Reply to this email directly, view it on GitHub<#4 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AN4WX5SNFNUXXKA2EYWLLZTRUUSFFANCNFSM4MET32FQ>.

[LZQhardworker]

you can just run python test.py

[qingyun322]

running python test.py will start the training process instead of inference. Can you update it?

[LZQhardworker]

it is actually test 获取 Outlook for iOS<https://aka.ms/o0ukef>

…

________________________________ 发件人: Qingyun Wang <[email protected]> 发送时间: Tuesday, June 2, 2020 10:38:06 PM 收件人: switchablenorms/DeepFashion_Try_On <[email protected]> 抄送: Yang; Han <[email protected]>; Comment <[email protected]> 主题: Re: [switchablenorms/DeepFashion_Try_On] how to inference model use other image? (#4) running python test.py will start the training process instead of inference. Can you update it? ― You are receiving this because you commented. Reply to this email directly, view it on GitHub<#4 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AN4WX5XT3SVA2PRV5PUBYGTRUUFE5ANCNFSM4MET32FQ>.

[qingyun322]

Thanks for clarifying, I think I understand the code now! The generated image will store in the 'sample' folder. Would you share some more information on data-preprocessing? I image that the labels are obtained from some segmentation model, the pose are obtained from openpose, is that right? What is the 'edge' variable?

[kelisiya]

Thanks for your work