**_config in train.py optimizer definition

kaixin96 / PANet

Code for our ICCV 2019 paper PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment

320 stars 64 forks source link

**_config in train.py optimizer definition #38

Closed ruohuali closed 3 years ago

ruohuali commented 3 years ago

Hello Why in train.py's optimizer definition _config is used instead of _config? `optimizer = torch.optim.SGD(model.parameters(), _config['optim']) This caused error when I tried to run train.py optimizer = torch.optim.SGD(model.parameters(), **_config['optim']) KeyError: 'optim' ` Thx for the help!

DpDark commented 3 years ago

Hello, I have the same problem. How did you solve it？

2679622694 commented 3 years ago

I have the same question

sharmaannapurna commented 3 years ago

HI, I am getting the same error when I tried to run the code. Any workaround?

ruohuali commented 3 years ago

I vaguely recall that it was a mistake about using wrong setup in config.py (I used test when it should be train or something like that).