1

I am new to deep learning, I have a yolov3 model that I have been training on my custom data. Every time I train, the training seems to start from scratch. How do I make the model continue its training from where it stopped last time? The setup I have is the same as this repo.

elbashmubarmeg
  • 330
  • 1
  • 9

1 Answers1

1

You can use model.load_weights(path_to_checkpoint) just after the model is defined at line 41 in train.py and continue training where you left off

Jitesh Malipeddi
  • 2,150
  • 3
  • 17
  • 37
  • Thank you! I am assuming the 'path_to_checkpoint' would be './"yolov3"' ? Because the training generates a 'yolov3.data-00000-of-00001' file, and I can't input that name into the load_weights method. I see in the script that do model.save_weights(./"yolov3"). – elbashmubarmeg Apr 03 '21 at 02:33