Yinan.Zhou

finally find property super parameters for mini-imagenet

5

after a lot of attemptions,i finally found a robust parameters to re-implement the refined cosine distance method: 1.we rewrite the cosine distance code. 2. we set scale factor s =...

can't reach the accuracy as report

17

I have train your code with loss_type = 'dist' & train_aug（baseline++）,but the 5 shot accuracy on mini-imagenet is only 56%,much lower than your report(66%)，could you give a resonable explaination?

is there something wrong with hard negative mining?

3

the implement of hard negative mining actually decrease the anchor number so when positive number = 0,negative number will be = 0 too