com.intel.analytics.zoo.pipeline.api.keras2.layers
Size of the region to which max pooling is applied. Integer. Default is 2.
Factor by which to downscale. Integer, or -1. 2 will halve the input. If -1, it will default to poolSize. Default is -1.
One of "valid"
or "same"
(case-insensitive). Default is 'valid'.
Either 'valid' or 'same'.
Either 'valid' or 'same'. Default is 'valid'.
Build graph: some other modules point to current module
Build graph: some other modules point to current module
upstream variables
Variable containing current module
One of "valid"
or "same"
(case-insensitive).
One of "valid"
or "same"
(case-insensitive). Default is 'valid'.
Size of the region to which max pooling is applied.
Size of the region to which max pooling is applied. Integer. Default is 2.
Size of the region to which max pooling is applied.
Size of the region to which max pooling is applied. Integer. Default is 2.
Factor by which to downscale.
Factor by which to downscale. Integer, or -1. 2 will halve the input. If -1, it will default to poolLength. Default is -1.
Factor by which to downscale.
Factor by which to downscale. Integer, or -1. 2 will halve the input. If -1, it will default to poolSize. Default is -1.
(Since version 0.3.0) please use recommended saveModule(path, overWrite)
Max pooling operation for temporal data.
Input shape 3D tensor with shape:
(batch_size, steps, features)
.Output shape 3D tensor with shape:
(batch_size, downsampled_steps, features)
.Numeric type of parameter(e.g. weight, bias). Only support float/double now