Zheng Rui

keep param order as model is an OrderedDict: ```python from collections import OrderedDict from torch.utils.model_zoo import load_url import torch sd = load_url("https://s3-us-west-2.amazonaws.com/jcjohns-models/vgg19-d01eb7cb.pth") map = {'classifier.1.weight':u'classifier.0.weight', 'classifier.1.bias':u'classifier.0.bias', 'classifier.4.weight':u'classifier.3.weight', 'classifier.4.bias':u'classifier.3.bias'} sd =...

Hi @efiop , thanks for the great tool you guys are building . I have a question, from my test recently, it is working fine if I put cache or...

Thanks @efiop , looking forward to the new features :) keep up the great work !

I am facing the same issue right now, is there any solution to this?

i submitted a pull request for this: https://github.com/gpleiss/efficient_densenet_pytorch/pull/39

Finally I decided to use the Pytorch pre-trained model, https://github.com/gpleiss/efficient_densenet_pytorch/issues/13

I guess it is this one: https://arxiv.org/abs/1711.08766v2