Contains classes for neural network 2D transposed convolution layer.
More...
|
| class | Batch< algorithmFPType, method > |
| | Computes the result of the forward and backward 2D transposed convolution layer of neural network in the batch processing mode. More...
|
| |
| struct | KernelSizes |
| | Data structure representing the size of the two-dimensional kernel subtensor. More...
|
| |
| struct | Strides |
| | Data structure representing the intervals on which the subtensors for 2D transposed convolution are selected. More...
|
| |
| struct | Paddings |
| | Data structure representing the number of data elements to implicitly add to each size of the two-dimensional subtensor on which 2D transposed convolution is performed. More...
|
| |
| struct | Indices |
| | Data structure representing the indices of the two dimensions on which 2D transposed convolution is performed. More...
|
| |
| struct | ValueSizes |
| | Data structure representing the value sizes of the two dimensions on which 2D transposed convolution is performed. More...
|
| |
| class | Parameter |
| | 2D transposed convolution layer parameters More...
|
| |
Available identifiers of results of the forward 2D transposed convolution layer and input objects for the backward 2D transposed convolution layer
| Enumerator |
|---|
| auxData |
Data processed at the forward stage of the layer
|
| auxWeights |
Input weights for forward stage of the layer
|
Available methods to compute forward and backward 2D transposed convolution layer
| Enumerator |
|---|
| defaultDense |
Default: performance-oriented method.
|