Maxout layer
layer_maxout(object, num_units, axis = -1, ...)
| object | Model or layer object |
|---|---|
| num_units | Specifies how many features will remain after maxout in the axis dimension (usually channel). This must be a factor of number of features. |
| axis | The dimension where max pooling will be performed. Default is the last dimension. |
| ... | additional parameters to pass |
A tensor
"Maxout Networks" Ian J. Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron Courville, Yoshua Bengio. https://arxiv.org/abs/1302.4389 Usually the operation is performed in the filter/channel dimension. This can also be used after Dense layers to reduce number of features.