Trainable=False or Trainable = "True" in Finetune

[aynesss]

I do a finetune of pretrained network, I would like to know,please, in finetune level, I must make trainable =True or False ? for layer in baseModel.layers: layer.trainable = True

[chentingpc]

depends on whether you'd like to fine-tune all weights, which typically yields better results.