Did you use pretrained models for training all fine-grained datasets?

[zzzucf]

In your paper, figure 6 showed all results for fine-grained datasets. However, when I tried to reproduce the results in bird dataset, I can only get 53% acc. Did you use any pre-trained model for training that? And can you post the code that can be helpful to reproduce your paper's result? Best regards.

[goldentimecoolk]

I have the same problem, getting ~52% accuracy in bird test dataset. I guess data_transforms might be one tricky, because parameters including mean, std, eigval, eigvec are calculated in ImageNet dataset. Pre-train maybe another tricky. Do you improve the accuracy? @zzzucf

[zzzucf]

use their pretrained mode and You can find the transform in pytorch site which is the same as their then u can repoduce the result.

[goldentimecoolk]

I used their pretrained model and got 80%+ accuracy in cub200 just now. As for transform, do you mean params they provide based on Imagenet dont need to be modified?

[zzzucf]

No need to change. goldentimecoolk <[email protected]>于2019年4月11日 周四上午9:16写道：

…

I used their pretrained model and got 80%+ accuracy in cub200 just now. As for transform, do you mean params they provide based on Imagenet dont need to be modified? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#3 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ADQ_Yx01CefBYE6zcvgF1LWFdZE92Ahsks5vfzWegaJpZM4Xk-NN> .