The issue about @slim.add_arg_scope

[zzzzzz0407]

I'm sorry that I am a newcomer to tensorflow, i am no familiar with the [email protected]_arg_scope at about line 45, is that mean you want to share the default params to the function (_inverted_residual_bottleneck), but if it just what i think, why do you not set the same [email protected]_arg_scope just at the func(mobilenet_v2_base)? And why we should set the @slim.add_arg_scope?I just think that slim.conv2d and slim.separable_conv2d can get the default params automatically. May the issue is foolish, please help me!

[ChiefGodMan]

I'm sorry I don't understand your question. Can you give me more information about mobilenet_v2_base code ? Nevertheless, you don't need to change any other code except replacing your loss function with focal loss. Best regards!