Package-level declarations
Types
Represents how the three output channels are ordered in memory.
Represents how the individual channels per pixel are arranged in memory.
Represents a GPU-accelerated Frame resizer and converter.
Configures options for a Resizer.
Functions
Create a new Resizer with the given ResizerOptions (the equivalent of VisionCamera's createResizer).
Gets a direct ByteBuffer over this GPUFrame's mapped Vulkan output memory, without copying (the equivalent of VisionCamera's zero-copy getPixelBuffer() ArrayBuffer), in the native byte order. It can be passed as is to ML runtimes such as LiteRT (TensorFlow Lite) or ONNX Runtime.
Gets an NSData over this GPUFrame's shared Metal output buffer, without copying (the equivalent of VisionCamera's zero-copy getPixelBuffer() ArrayBuffer). Its bytes can be passed as is to ML runtimes, e.g. to a Core ML MLMultiArray(dataPointer:...).
Returns whether the GPU-accelerated Resizer pipeline is available on this device.