Closed johnnylu305 closed 4 years ago
yes, no matter train from 'init' or from 'cls', the final performance is the same. I have tested on my computer. A few days ago, another researcher told me he/she cannot get the result using the 'init', I have found some bugs and fixed it. If you cannot get the result, please let me know, I will check it again.
@zbf1991 Thank you for your explanation. Sorry, I forgot to ask another minor question. Why you set densecrfloss to 1e-7? Doesn't it disable your energy loss?
I think densecrfloss is just a hyperparameter to adjust energy loss. This is because the value of energy loss is very small(ex: -4700377).
Hi, nice to meet you. There are two pretrain weights about your classification network. One is "ilsvrc-cls_rna-a1_cls1000_ep-0001.params" and another one is "res38_cls.pth". My question is that can people get the same result in your paper if they train from "ilsvrc-cls_rna-a1_cls1000_ep-0001.params"?