search

cosmic-cortex / pytorch-UNet

2D and 3D UNet implementation in PyTorch.
MIT License
147 stars 40 forks source link

training results #3

Open 15793723081 opened 4 years ago

15793723081 commented 4 years ago

Hello, I got val_loss, f1 and train_loss by using my own data training volume networkIs it convenient to provide your training results?I want to make a reference.

cosmic-cortex commented 4 years ago

Hi! I am not sure what you mean by convenient to provide your training results. If I understand it correctly, training results are often reported, but validation and test losses are much more important. If you are writing a paper, you should definitely report validation losses. Let me know if this is what you meant!

15793723081 commented 4 years ago

Thank you for your reply. I would like to know the logs.csv in your results. I trained with my own data and would like to make a reference to see if my training results are correct.

------------------ 原始邮件 ------------------ 发件人: "Tivadar Danka"<notifications@github.com>; 发送时间: 2019年11月19日(星期二) 晚上7:53 收件人: "cosmic-cortex/pytorch-UNet"<pytorch-UNet@noreply.github.com>; 抄送: "时光里的流沙"<1335578176@qq.com>;"Author"<author@noreply.github.com>; 主题: Re: [cosmic-cortex/pytorch-UNet] training results (#3)

Hi! I am not sure what you mean by convenient to provide your training results. If I understand it correctly, training results are often reported, but validation and test losses are much more important. If you are writing a paper, you should definitely report validation losses. Let me know if this is what you meant!

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.