Continue to train on the trained model

[ascacdsaa]

Dear author, can your code continue to train on the basis of the trained model? What should be changed? Thank you.

[yinbow]

You can load the weight of the trained model by adding the following code after the definition of the model at train.py (line 192):

weight=torch.load(your_model_path)['model']
model.load_state_dict(weight)

[ascacdsaa]

Thank you very much for your reply. It has been very helpful to me.