search

jiangtaoxie / fast-MPN-COV

@CVPR2018: Efficient unrolling iterative matrix square-root normalized ConvNets, implemented by PyTorch (and code of B-CNN,Compact bilinear pooling etc.) for training from scratch & finetuning.
http://peihuali.org/iSQRT-COV/index.html
MIT License
270 stars 56 forks source link

what's the meaning of Implementations? #3

Closed Deeplearning20 closed 6 years ago

Deeplearning20 commented 6 years ago

Hello, I don't know what the meaning of three points in Implementations.

  1. Is the experiment implemented in three ways, in pytorch or tensorflow or MatConvNet?
    1. Or use pytorch first? then tensorflow? and finally MatConvNet? 3.Or use MatConvNet in the pytorch environment (or use MatConvNet in the tensorflow environment)? My question may be naive .Thanks very much if can hear from you. image
jiangtaoxie commented 6 years ago

@Deeplearning20 Hi, there may be some misunderstandings here. The three implementations we provide are independent of each other. For example, if you are a PyTorch user, you can ignore the others and only care about the contents of the PyTorch/ folder.

Deeplearning20 commented 6 years ago

I understand that!Thanks very much!