zorrocai

The faster rcnn don't have this problem. So I think the bug lies in the differences between faster rcnn and RFCN, not the version.

@GYxiaOH Thanks for the notice.

@lxtGH Sorry, I was busy with other project those days. I don't locate the problem.

@naren142 No, I didn't. I just try to rewrite D&T in pytorch.

Hi, every one. I have rewritten the D&T architecture in pytorch, but I found that there are so many tricks to achieve the original result in the paper, like data...

@naren142 [email protected]

Are your per-class mean hidden representations based on batch size samples? so is your accuracy?

Thanks for your guides. I have prepared the IELTS test those days. Actually, instead of using the eigenvalue decomposition in LDA first, I tried to learn the projection matrix A...

I have trained the AlexNet with lda-eigenvalues loss.But here wasn't any good improvement on train accuracy. The sample outputs of my code listed below: epoch 13 avg_train_loss: -0.999989 ('LDA-Eigenvalues (Train):',...

Actually, I run into such a situation: S_B/S_W becomes a minus identity matrix druing training.So the eigenvalues are all 1. this condition may prevent further training.  I really don't...