search

codeslake / Color_Transfer_Histogram_Analogy

[CGI 2020] Official PyTorch Implementation for "Deep Color Transfer using Histogram Analogy"
GNU Affero General Public License v3.0
166 stars 32 forks source link

When I try to turn on semantic replacement, I met a bug as follows : #10

Closed lsfhuihuiff closed 2 years ago

lsfhuihuiff commented 2 years ago

RuntimeError: output with shape[1,1024,768] dosen't match the broadcast shape[3,1024,768] I check the segmentation of image is 3 channels. Could you please tell me how I can solve this problem?

codeslake commented 2 years ago

Hi, @lsfhuihuiff.

Where exactly does the error occur?

codeslake commented 2 years ago

Hi, @lsfhuihuiff.

I am closing the issue as it has been a week since my last comment. Please reopen this issue if you still have a problem!

lsfhuihuiff commented 2 years ago

Dear JunyongLee，

Thank you for your reply. I'm sorry I didn't check my messages in time. In fact ,I do not know how to join the segmentation image module.Are there some specific requirements for image segmentation? It would be great if you would like to enrich the use of this section in the Readme section .

Thank you very much！ Have a good day! Sifei Li

发件人：Junyong Lee @.> 发送日期：2021-12-09 22:24:52 收件人：codeslake/Color_Transfer_Histogram_Analogy @.> 抄送人：lsfhuihuiff @.>,Mention @.> 主题：Re: [codeslake/Color_Transfer_Histogram_Analogy] When I try to turn on semantic replacement, I met a bug as follows : (Issue #10)

Hi, @lsfhuihuiff. Where exactly does the error occur? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.

codeslake commented 2 years ago

Hi, @lsfhuihuiff.

You may refer here for more details about the segmentation map.

Best,