You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In your current implementation, each PReLU layer has as many trainable parameters as the number of elements in the input (HxWxC) whereas in other implementations (deepinsight's insightface or TMaysGGS's MobileFaceNet-Keras have only one trainable parameter per channel.
Indeed, in Keras, the default argument for the shared_axes parameter of PReLU ("the axes along which to share learnable parameters for the activation function") is None. So you have to specify shared_axes=[1,2] in the calls to PReLU in order to keep the number of trainable parameters reasonable and match other implementations.
In your current implementation, each
PReLU
layer has as many trainable parameters as the number of elements in the input (HxWxC) whereas in other implementations (deepinsight
'sinsightface
orTMaysGGS
'sMobileFaceNet-Keras
have only one trainable parameter per channel.Indeed, in Keras, the default argument for the
shared_axes
parameter of PReLU ("the axes along which to share learnable parameters for the activation function") isNone
. So you have to specifyshared_axes=[1,2]
in the calls toPReLU
in order to keep the number of trainable parameters reasonable and match other implementations.Reference: https://keras.io/layers/advanced-activations/
The text was updated successfully, but these errors were encountered: