DBNet icon indicating copy to clipboard operation
DBNet copied to clipboard
verified publisher icon zonasw

why batch norm layer freeze?

Open gynjimmy0306 opened this issue 5 years ago • 0 comments

in batch norm layer setting layer.trainable = False means freeze the layer, i.e. its internal state will not change during training: its trainable weights will not be updated during fit() or train_on_batch(), and its state updates will not be run，why batch norm freeze in train code?

gynjimmy0306 avatar Nov 02 '20 09:11 gynjimmy0306