LiteRT を使ってみる

public Interpreter(@NotNull File modelFile);

public Interpreter(@NotNull MappedByteBuffer mappedByteBuffer);

try (Interpreter interpreter = new Interpreter(file_of_tensorflowlite_model)) {
  Map<String, Object> inputs = new HashMap<>();
  inputs.put("input_1", input1);
  inputs.put("input_2", input2);
  Map<String, Object> outputs = new HashMap<>();
  outputs.put("output_1", output1);
  interpreter.runSignature(inputs, outputs, "mySignature");
}

try (Interpreter interpreter = new Interpreter(file_of_a_tensorflowlite_model)) {
  interpreter.run(input, output);
}

interpreter.runForMultipleInputsOutputs(inputs, map_of_indices_to_outputs);

public int getInputIndex(String opName);
public int getOutputIndex(String opName);

interpreter.close();

import TensorFlowLite

// Getting model path
guard
  let modelPath = Bundle.main.path(forResource: "model", ofType: "tflite")
else {
  // Error handling...
}

do {
  // Initialize an interpreter with the model.
  let interpreter = try Interpreter(modelPath: modelPath)

  // Allocate memory for the model's input `Tensor`s.
  try interpreter.allocateTensors()

  let inputData: Data  // Should be initialized

  // input data preparation...

  // Copy the input data to the input `Tensor`.
  try self.interpreter.copy(inputData, toInputAt: 0)

  // Run inference by invoking the `Interpreter`.
  try self.interpreter.invoke()

  // Get the output `Tensor`
  let outputTensor = try self.interpreter.output(at: 0)

  // Copy output to `Data` to process the inference results.
  let outputSize = outputTensor.shape.dimensions.reduce(1, {x, y in x * y})
  let outputData =
        UnsafeMutableBufferPointer<Float32>.allocate(capacity: outputSize)
  outputTensor.data.copyBytes(to: outputData)

  if (error != nil) { /* Error handling... */ }
} catch error {
  // Error handling...
}

@import TensorFlowLite;

NSString *modelPath = [[NSBundle mainBundle] pathForResource:@"model"
                                                      ofType:@"tflite"];
NSError *error;

// Initialize an interpreter with the model.
TFLInterpreter *interpreter = [[TFLInterpreter alloc] initWithModelPath:modelPath
                                                                  error:&error];
if (error != nil) { /* Error handling... */ }

// Allocate memory for the model's input `TFLTensor`s.
[interpreter allocateTensorsWithError:&error];
if (error != nil) { /* Error handling... */ }

NSMutableData *inputData;  // Should be initialized
// input data preparation...

// Get the input `TFLTensor`
TFLTensor *inputTensor = [interpreter inputTensorAtIndex:0 error:&error];
if (error != nil) { /* Error handling... */ }

// Copy the input data to the input `TFLTensor`.
[inputTensor copyData:inputData error:&error];
if (error != nil) { /* Error handling... */ }

// Run inference by invoking the `TFLInterpreter`.
[interpreter invokeWithError:&error];
if (error != nil) { /* Error handling... */ }

// Get the output `TFLTensor`
TFLTensor *outputTensor = [interpreter outputTensorAtIndex:0 error:&error];
if (error != nil) { /* Error handling... */ }

// Copy output to `NSData` to process the inference results.
NSData *outputData = [outputTensor dataWithError:&error];
if (error != nil) { /* Error handling... */ }

#include "tensorflow/lite/c/c_api.h"

TfLiteModel* model = TfLiteModelCreateFromFile([modelPath UTF8String]);
TfLiteInterpreterOptions* options = TfLiteInterpreterOptionsCreate();

// Create the interpreter.
TfLiteInterpreter* interpreter = TfLiteInterpreterCreate(model, options);

// Allocate tensors and populate the input tensor data.
TfLiteInterpreterAllocateTensors(interpreter);
TfLiteTensor* input_tensor =
    TfLiteInterpreterGetInputTensor(interpreter, 0);
TfLiteTensorCopyFromBuffer(input_tensor, input.data(),
                           input.size() * sizeof(float));

// Execute inference.
TfLiteInterpreterInvoke(interpreter);

// Extract the output tensor data.
const TfLiteTensor* output_tensor =
    TfLiteInterpreterGetOutputTensor(interpreter, 0);
TfLiteTensorCopyToBuffer(output_tensor, output.data(),
                         output.size() * sizeof(float));

// Dispose of the model and interpreter objects.
TfLiteInterpreterDelete(interpreter);
TfLiteInterpreterOptionsDelete(options);
TfLiteModelDelete(model);

class FlatBufferModel {
  // Build a model based on a file. Return a nullptr in case of failure.
  static std::unique_ptr<FlatBufferModel> BuildFromFile(
      const char* filename,
      ErrorReporter* error_reporter);

  // Build a model based on a pre-loaded flatbuffer. The caller retains
  // ownership of the buffer and should keep it alive until the returned object
  // is destroyed. Return a nullptr in case of failure.
  static std::unique_ptr<FlatBufferModel> BuildFromBuffer(
      const char* buffer,
      size_t buffer_size,
      ErrorReporter* error_reporter);
};

// Load the model
std::unique_ptr<tflite::FlatBufferModel> model =
    tflite::FlatBufferModel::BuildFromFile(filename);

// Build the interpreter
tflite::ops::builtin::BuiltinOpResolver resolver;
std::unique_ptr<tflite::Interpreter> interpreter;
tflite::InterpreterBuilder(*model, resolver)(&interpreter);

// Resize input tensors, if needed.
interpreter->AllocateTensors();

float* input = interpreter->typed_input_tensor<float>(0);
// Fill `input`.

interpreter->Invoke();

float* output = interpreter->typed_output_tensor<float>(0);

$ python3 -m pip install ai-edge-litert

from ai_edge_litert.interpreter import Interpreter
Interpreter = Interpreter(model_path=args.model.file)

class TestModel(tf.Module):
  def __init__(self):
    super(TestModel, self).__init__()

  @tf.function(input_signature=[tf.TensorSpec(shape=[1, 10], dtype=tf.float32)])
  def add(self, x):
    '''
    Simple method that accepts single input 'x' and returns 'x' + 4.
    '''
    # Name the output 'result' for convenience.
    return {'result' : x + 4}

SAVED_MODEL_PATH = 'content/saved_models/test_variable'
TFLITE_FILE_PATH = 'content/test_variable.tflite'

# Save the model
module = TestModel()
# You can omit the signatures argument and a default signature name will be
# created with name 'serving_default'.
tf.saved_model.save(
    module, SAVED_MODEL_PATH,
    signatures={'my_signature':module.add.get_concrete_function()})

# Convert the model using TFLiteConverter
converter = tf.lite.TFLiteConverter.from_saved_model(SAVED_MODEL_PATH)
tflite_model = converter.convert()
with open(TFLITE_FILE_PATH, 'wb') as f:
  f.write(tflite_model)

# Load the LiteRT model in LiteRT Interpreter
from ai_edge_litert.interpreter import Interpreter
interpreter = Interpreter(TFLITE_FILE_PATH)

# There is only 1 signature defined in the model,
# so it will return it by default.
# If there are multiple signatures then we can pass the name.
my_signature = interpreter.get_signature_runner()

# my_signature is callable with input as arguments.
output = my_signature(x=tf.constant([1.0], shape=(1,10), dtype=tf.float32))
# 'output' is dictionary with all outputs from the inference.
# In this case we have single output 'result'.
print(output['result'])

import numpy as np
import tensorflow as tf

# Load the LiteRT model and allocate tensors.
from ai_edge_litert.interpreter import Interpreter
interpreter = Interpreter(TFLITE_FILE_PATH)
interpreter.allocate_tensors()

# Get input and output tensors.
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()

# Test the model on random input data.
input_shape = input_details[0]['shape']
input_data = np.array(np.random.random_sample(input_shape), dtype=np.float32)
interpreter.set_tensor(input_details[0]['index'], input_data)

interpreter.invoke()

# The function `get_tensor()` returns a copy of the tensor data.
# Use `tensor()` in order to get a pointer to the tensor.
output_data = interpreter.get_tensor(output_details[0]['index'])
print(output_data)

import numpy as np
import tensorflow as tf

img = tf.keras.Input(shape=(64, 64, 3), name="img")
const = tf.constant([1., 2., 3.]) + tf.constant([1., 4., 4.])
val = img + const
out = tf.identity(val, name="out")

# Convert to LiteRT format
converter = tf.lite.TFLiteConverter.from_keras_model(tf.keras.models.Model(inputs=[img], outputs=[out]))
tflite_model = converter.convert()

# Load the LiteRT model and allocate tensors.
from ai_edge_litert.interpreter import Interpreter
interpreter = Interpreter(model_content=tflite_model)
interpreter.allocate_tensors()

# Continue to get tensors and so forth, as shown above...

// Resize input tensors before allocate tensors
interpreter->ResizeInputTensor(/*tensor_index=*/0, std::vector<int>{3,10});
interpreter->AllocateTensors();

# Load the LiteRT model in LiteRT Interpreter
from ai_edge_litert.interpreter import Interpreter
interpreter = Interpreter(model_path=TFLITE_FILE_PATH)

# Resize input shape for dynamic shape model and allocate tensor
interpreter.resize_tensor_input(interpreter.get_input_details()[0]['index'], [3, 10])
interpreter.allocate_tensors()

# Get input and output tensors.
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()