search

sudipansaha / dcvaVHROptical

Deep Change Vector Analysis
BSD 2-Clause "Simplified" License
52 stars 9 forks source link

Question about loading pretrained_model in dcva.py and dcvaUnequalRowColumn.py #13

Closed a109012419 closed 1 year ago

a109012419 commented 1 year ago

On line 138 : state_dictForLayer23={k: v for k, v in netForFeatureExtractionLayer23Dict.items() if k in state_dictForLayer23} netForFeatureExtractionLayer23Dict.items() seems to be a dictionary of randomly initialized parameters, while state_dictForLayer23 is the real pretrained_model. "for k, v in netF...items()" retains the weight in the random parameter. So this line of code seems to just load random parameters into the network. Nevertheless, thank you very much for migrating the code in matlab to the python version for us to learn.

sudipansaha commented 1 year ago

Thanks for pointing it, had found the issue but forgot to update here. Updated now.