training results

[15793723081]

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]

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]

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.

…

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