มอบสิทธิ์การเร่งความเร็วของ GPU สำหรับ iOS

import TensorFlowLite

// Load model ...

// Initialize LiteRT interpreter with the GPU delegate.
let delegate = MetalDelegate()
if let interpreter = try Interpreter(modelPath: modelPath,
                                      delegates: [delegate]) {
  // Run inference ...
}
      

// Import module when using CocoaPods with module support
@import TFLTensorFlowLite;

// Or import following headers manually
#import "tensorflow/lite/objc/apis/TFLMetalDelegate.h"
#import "tensorflow/lite/objc/apis/TFLTensorFlowLite.h"

// Initialize GPU delegate
TFLMetalDelegate* metalDelegate = [[TFLMetalDelegate alloc] init];

// Initialize interpreter with model path and GPU delegate
TFLInterpreterOptions* options = [[TFLInterpreterOptions alloc] init];
NSError* error = nil;
TFLInterpreter* interpreter = [[TFLInterpreter alloc]
                                initWithModelPath:modelPath
                                          options:options
                                        delegates:@[ metalDelegate ]
                                            error:&error];
if (error != nil) { /* Error handling... */ }

if (![interpreter allocateTensorsWithError:&error]) { /* Error handling... */ }
if (error != nil) { /* Error handling... */ }

// Run inference ...
      

// Set up interpreter.
auto model = FlatBufferModel::BuildFromFile(model_path);
if (!model) return false;
tflite::ops::builtin::BuiltinOpResolver op_resolver;
std::unique_ptr<Interpreter> interpreter;
InterpreterBuilder(*model, op_resolver)(&interpreter);

// Prepare GPU delegate.
auto* delegate = TFLGpuDelegateCreate(/*default options=*/nullptr);
if (interpreter->ModifyGraphWithDelegate(delegate) != kTfLiteOk) return false;

// Run inference.
WriteToInputTensor(interpreter->typed_input_tensor<float>(0));
if (interpreter->Invoke() != kTfLiteOk) return false;
ReadFromOutputTensor(interpreter->typed_output_tensor<float>(0));

// Clean up.
TFLGpuDelegateDelete(delegate);
      

#include "tensorflow/lite/c/c_api.h"
#include "tensorflow/lite/delegates/gpu/metal_delegate.h"

// Initialize model
TfLiteModel* model = TfLiteModelCreateFromFile(model_path);

// Initialize interpreter with GPU delegate
TfLiteInterpreterOptions* options = TfLiteInterpreterOptionsCreate();
TfLiteDelegate* delegate = TFLGPUDelegateCreate(nil);  // default config
TfLiteInterpreterOptionsAddDelegate(options, metal_delegate);
TfLiteInterpreter* interpreter = TfLiteInterpreterCreate(model, options);
TfLiteInterpreterOptionsDelete(options);

TfLiteInterpreterAllocateTensors(interpreter);

NSMutableData *input_data = [NSMutableData dataWithLength:input_size * sizeof(float)];
NSMutableData *output_data = [NSMutableData dataWithLength:output_size * sizeof(float)];
TfLiteTensor* input = TfLiteInterpreterGetInputTensor(interpreter, 0);
const TfLiteTensor* output = TfLiteInterpreterGetOutputTensor(interpreter, 0);

// Run inference
TfLiteTensorCopyFromBuffer(input, inputData.bytes, inputData.length);
TfLiteInterpreterInvoke(interpreter);
TfLiteTensorCopyToBuffer(output, outputData.mutableBytes, outputData.length);

// Clean up
TfLiteInterpreterDelete(interpreter);
TFLGpuDelegateDelete(metal_delegate);
TfLiteModelDelete(model);
      

// THIS:
var options = MetalDelegate.Options()
options.isPrecisionLossAllowed = false
options.waitType = .passive
options.isQuantizationEnabled = true
let delegate = MetalDelegate(options: options)

// IS THE SAME AS THIS:
let delegate = MetalDelegate()
      

// THIS:
TFLMetalDelegateOptions* options = [[TFLMetalDelegateOptions alloc] init];
options.precisionLossAllowed = false;
options.waitType = TFLMetalDelegateThreadWaitTypePassive;
options.quantizationEnabled = true;

TFLMetalDelegate* delegate = [[TFLMetalDelegate alloc] initWithOptions:options];

// IS THE SAME AS THIS:
TFLMetalDelegate* delegate = [[TFLMetalDelegate alloc] init];
      

// THIS:
const TFLGpuDelegateOptions options = {
  .allow_precision_loss = false,
  .wait_type = TFLGpuDelegateWaitType::TFLGpuDelegateWaitTypePassive,
  .enable_quantization = true,
};

TfLiteDelegate* delegate = TFLGpuDelegateCreate(options);

// IS THE SAME AS THIS:
TfLiteDelegate* delegate = TFLGpuDelegateCreate(nullptr);
      

#include "tensorflow/lite/delegates/gpu/metal_delegate.h"
#include "tensorflow/lite/delegates/gpu/metal_delegate_internal.h"

// ...

// Prepare GPU delegate.
auto* delegate = TFLGpuDelegateCreate(nullptr);

if (interpreter->ModifyGraphWithDelegate(delegate) != kTfLiteOk) return false;

interpreter->SetAllowBufferHandleOutput(true);  // disable default gpu->cpu copy
if (!TFLGpuDelegateBindMetalBufferToTensor(
        delegate, interpreter->inputs()[0], user_provided_input_buffer)) {
  return false;
}
if (!TFLGpuDelegateBindMetalBufferToTensor(
        delegate, interpreter->outputs()[0], user_provided_output_buffer)) {
  return false;
}

// Run inference.
if (interpreter->Invoke() != kTfLiteOk) return false;
      

    var options = MetalDelegate.Options()
    options.isQuantizationEnabled = false
    let delegate = MetalDelegate(options: options)
      

    TFLMetalDelegateOptions* options = [[TFLMetalDelegateOptions alloc] init];
    options.quantizationEnabled = false;
      

    TFLGpuDelegateOptions options = TFLGpuDelegateOptionsDefault();
    options.enable_quantization = false;

    TfLiteDelegate* delegate = TFLGpuDelegateCreate(options);