search

easezyc / deep-transfer-learning

A collection of implementations of deep domain adaptation algorithms
MIT License
889 stars 205 forks source link

A supplement to dataset of DAN #4

Closed MiaoHaoSunny closed 4 years ago

MiaoHaoSunny commented 5 years ago

if you are in a situation where soft-loss is equal to 0 and accuracy is 100%, you probably meet the same problem as me. You might need to check your dataset and ensure that sub-classes are under the category folder such as bike and back_pack instead of images. The correct data set layout is shown in the figure. I hope this works and can help you. 示例图片

easezyc commented 5 years ago

Thanks for your contribution.

459548764 commented 5 years ago

Very useful !!!

slowlyswimming commented 4 years ago

The accuracy goes under 100% now. Great tips.

VoiceBeer commented 4 years ago

Thx for the tip, I think this issue should be added into the README.md

MoriZSJ commented 3 years ago

Helpful supplement! Thanks 😊

heeler-deer commented 11 months ago

helpful, thanks