MhLiao / MaskTextSpotterV3

The code of "Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting"
Other
628 stars 121 forks source link

About the initialization of the amp #40

Open czh0001 opened 4 years ago

czh0001 commented 4 years ago

Hello, I found that in the train_net.py, the initialization of the amp uses 'model, optimizer = amp.initialize(model, optimizer, opt_level=amp_opt_level)' and in the test_net.py, the initialization of the amp uses 'amp_handle = amp.init(enabled=use_mixed_precision, verbose=cfg.AMP_VERBOSE)' instead. What is the difference of them?