reachsumit / deep-unet-for-satellite-image-segmentation

Satellite Imagery Feature Detection with SpaceNet dataset using deep UNet
308 stars 138 forks source link

How to convert the project with "PyTorch"? #27

Open JenniferYingyiWu2020 opened 2 years ago

JenniferYingyiWu2020 commented 2 years ago

Hi, I have seen the deep learning is implemented with "Keras" in your project. However, if I would like to rewrite the model and training using "PyTorch", then how to do converting? 100 101

So, could you pls give me some suggestions? Thanks!
wenwuma commented 2 years ago

你好, @.***,你可以问问他。 祝好

------------------ 原始邮件 ------------------ 发件人: "reachsumit/deep-unet-for-satellite-image-segmentation" @.>; 发送时间: 2021年10月22日(星期五) 下午3:17 @.>; @.***>; 主题: [reachsumit/deep-unet-for-satellite-image-segmentation] How to convert the project with "PyTorch"? (Issue #27)

Hi, I have seen the deep learning is implemented with "Keras" in your project. However, if I would like to rewrite the model and training using "PyTorch", then how to do converting? So, could you pls give me some suggestions? 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.

JenniferYingyiWu2020 commented 2 years ago

Hi, The email address you have mentioned is masked, and I am so confused about it. @.*** So, could you pls tell me the detailed contact information? Thanks!

JenniferYingyiWu2020 commented 2 years ago

你好, 请问你上面的“标有星号*”的邮箱地址具体是怎样的呢?

wenwuma commented 2 years ago

你有试过这个地址吗 

------------------ 原始邮件 ------------------ 发件人: "Yingyi @.>; 发送时间: 2021年11月22日(星期一) 下午2:28 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [reachsumit/deep-unet-for-satellite-image-segmentation] How to convert the project with "PyTorch"? (Issue #27)

你好, 请问你上面的“标有星号*”的邮箱地址具体是怎样的呢?

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