adaptive_weighted_attribute

adaptive_weighted_attribute copied to clipboard

Hello, sorry to bother you with a question about the design of the weight λ

1

As mentioned in the paper, trend = abs(cur_mean - pre_mean) / cur_mean. So for one particular attribute, if cur_mean equals pre_mean, then trend = 0, norm_trend = 0 and λ...

623331069

Can you share the test code?

2

Can you share the test code? I test the model in CelebA dataset. But only get the 89% acc in the eyeglasses attributes.

ShaowenLin

hello, when i test the trained model, i get the error, can you help to solve the problem

kaiing