I am a student of the second year of Tsinghua graduate school. I sincerely ask a question: does it support real-time verification during training? For example, do you consider adding a new function, that is, each time you complete an epoch training, you will verify on the specified verification data set and print the loss on the verification set?

[xianglei3]

I am a student of the second year of Tsinghua graduate school. I sincerely ask a question: does it support real-time verification during training? For example, do you consider adding a new function, that is, each time you complete an epoch training, you will verify on the specified verification data set and print the loss on the verification set?

[xuebinqin]

Our code does support validation. This line " hypar["model_save_fre"] = 2000 ## valid and save model weights every 2000 iterations" controls the validation frequence.

On Mon, Jul 18, 2022 at 12:46 AM xianglei3 @.***> wrote:

I am a student of the second year of Tsinghua graduate school. I sincerely ask a question: does it support real-time verification during training? For example, do you consider adding a new function, that is, each time you complete an epoch training, you will verify on the specified verification data set and print the loss on the verification set?

— Reply to this email directly, view it on GitHub https://github.com/xuebinqin/U-2-Net/issues/318, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORPFTS6EVAUKV2G7D3DVUUDUXANCNFSM533JDHFQ . You are receiving this because you are subscribed to this thread.Message ID: @.***>

-- Xuebin Qin PhD Department of Computing Science University of Alberta, Edmonton, AB, Canada Homepage: https://xuebinqin.github.io/

[WZMIAOMIAO]

I am a student of the second year of Tsinghua graduate school. I sincerely ask a question: does it support real-time verification during training? For example, do you consider adding a new function, that is, each time you complete an epoch training, you will verify on the specified verification data set and print the loss on the verification set?

hi, you can refer this repo: https://github.com/WZMIAOMIAO/deep-learning-for-image-processing/tree/dev/pytorch_segmentation/u2net