Can share the super parameters to reproduce the result on CUB-200-2011?

[bjkite]

I use the super parameters given in the run script to reproduce the work of WeightLoss, but I can not get the same result as reported. My best result as follow:

Epoch-130 0.6411 0.7437 0.8301 0.8981 0.9458 0.9731

Would you please give me some help?

[bnu-wangxun]

Fisrt, the performance of CUB is not quite stable, you just need run more iteration with more times.
Second, the batch size should be 70-80, num_instance should be 5. Adam with 1e-5 learn rate. My result is always higher than 0.65 on CUB dataset.

And I suggest you try the SGD optimizer to replace ADAM, I try the SGD on Car, and a bit better performance than Adam.

[besran]

How about the parameters for In-Shop?

[bnu-wangxun]

Larger batchsize (> 200) is already enough. No other tricks.

[bnu-wangxun]

We rerun our script and the performance of Emenbedding size of 512 is as below:
Epoch-200 0.6595 0.7601 0.8427 0.9067 0.9465 0.9738

[bnu-wangxun]

@bjkite I think the problem of not get close performance exists in hard mining:
you should change the hard_mining in the loss: /losses/Weight.py

self.hard_mining = hard_mining

Make self.hard_mining not None.
Then you will get similar performance.
I will fix this problem in these days.