Calculates the shapes of the output of this layer for the given input shapes.
- iOS 11.2+
- macOS 10.13.2+
- Mac Catalyst 13.0+
- tvOS 11.2+
- watchOS 4.2+
- Core ML
The shapes of the input for this layer.
The shapes of the output for the given input shapes.
Implement this method to define the layer's interface with the rest of the network. It will be called at least once at load time and any time the size of the inputs changes in a call to
This method consumes and returns 5D arrays of shapes in the usual Core ML convention: Sequence, Batch, Channel, Height, and Width. See the Core ML Neural Network specification for more details about how layers use these dimensions.