The ScaledSoftSign is a modification of SoftSign activation function that has trainable parameters.
$$ScaledSoftSign(x) = \frac{\alpha x}{\beta + |x|}$$
Source: Trainable Activations for Image ClassificationPaper | Code | Results | Date | Stars |
---|
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |