Closed YoungJoongUNC closed 4 years ago
There is no need to fine-tune the provided model. If you learn it from scratch, you could use fine-tuning to improve. In addition, there is already code for fine-tuning and you just add "--f" when training(please check arguments in train.py).
Thank you! It worked :)
Hello! I wanted to load the model you provided for the evaluation (model.pt) and continue training. When I loaded it using the code in the eval.py, it shows following error. May I ask for an advice how could I solve this?
The code I am using in train.py is as follows:
The error I am getting is as follows: AttributeError: 'DataParallel' object has no attribute 'name'
Thank you!