search

WuJie1010 / Facial-Expression-Recognition.Pytorch

A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset
MIT License
1.77k stars 546 forks source link

Question about t7 file #104

Open ZangHuanyu opened 3 years ago

ZangHuanyu commented 3 years ago

Hi Wujie,

I have some questions about the t7 file, it may sound stupid.

So I know the t7 file stores the parameters or the model, but how can I export or print those in t7 file? I spent a lot of time online, but can't find anything useful.

Also why there are two different t7 files for public_test and private_test?

And I saw only under opt.resume condition, the code will load the t7 file. So if under such condition, it means directly load the file, if else, which means train from beginning, am I right?

Thanks a lot!

WuJie1010 commented 3 years ago

1）You can first use the model to load the T7 file, and then use the named_ parameters () to print; 2）There are two datasets, so there are two models, which are the best ckpt obtained in this dataset. 3 about "under opt.resume condition, the code will load the t7 file. So if under such condition, it means directly load the file, if else, which means train from beginning", you are right~