Int array of length 2. Kernel dim1 of the three cropping dimensions. Default is (1, 1).
Int array of length 2. Kernel dim2 of the three cropping dimensions. Default is (1, 1).
Int array of length 2. Kernel dim3 of the three cropping dimensions. Default is (1, 1).
Format of input data. Either 'CHANNEL_FIRST' (dimOrdering='th') or 'CHANNEL_LAST' (dimOrdering='tf'). Default is 'CHANNEL_FIRST'.
A Single Shape, does not include the batch dimension.
Int array of length 2.
Int array of length 2. Kernel dim1 of the three cropping dimensions. Default is (1, 1).
Int array of length 2.
Int array of length 2. Kernel dim2 of the three cropping dimensions. Default is (1, 1).
Int array of length 2.
Int array of length 2. Kernel dim3 of the three cropping dimensions. Default is (1, 1).
Format of input data.
Format of input data. Either 'CHANNEL_FIRST' (dimOrdering='th') or 'CHANNEL_LAST' (dimOrdering='tf'). Default is 'CHANNEL_FIRST'.
Build graph: some other modules point to current module
Build graph: some other modules point to current module
upstream variables
Variable containing current module
A Single Shape, does not include the batch dimension.
A Single Shape, does not include the batch dimension.
(Since version 0.3.0) please use recommended saveModule(path, overWrite)
Cropping layer for 3D data (e.g. spatial or spatio-temporal). The input of this layer should be 5D.
When you use this layer as the first layer of a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
Numeric type of parameter(e.g. weight, bias). Only support float/double now.