search

ShichenLiu / CondenseNet

CondenseNet: Light weighted CNN for mobile devices
MIT License
694 stars 131 forks source link

Transfer-learning with CondenseNet #15

Open BDimitri opened 6 years ago

BDimitri commented 6 years ago

Hello, I am getting good accuracy with CondenseNet on my dataset when training from scratch, but I feel like I could boost the results if I could train from a checkpoint pretrained on ImageNet. You offer the converted checkpoints on ImageNet, but my understanding of the situation is that I can't use that for transfer learning because its missing some dicts like the optimizer. Since I am new to pytorch I feel like I am missing something. Is it possible to train from the converted checkpoint? If no, would it be possible to upload the unconverted model?

ShichenLiu commented 5 years ago

Sorry for being late. As far as I know, you don't need the state dict of optimizer to do transfer learning. Just load the converted weight and train should be fine.