從舊版自訂模型 API 遷移

firebase-ml-model-interpreter 程式庫 22.0.2 版推出新的 getLatestModelFile() 方法,可取得裝置上自訂模型的位置。您可以使用這個方法直接例項化 TensorFlow Lite Interpreter 物件,取代 FirebaseModelInterpreter 包裝函式。

今後建議採用這種做法。由於 TensorFlow Lite 解譯器版本不再與 Firebase 程式庫版本連結,因此您可以更彈性地升級至新版 TensorFlow Lite,或更輕鬆地使用自訂 TensorFlow Lite 建構版本。

本頁面說明如何從使用 FirebaseModelInterpreter 遷移至 TensorFlow Lite Interpreter

1. 更新專案依附元件

更新專案的依附元件,加入 firebase-ml-model-interpreter 程式庫 22.0.2 版 (或更新版本) 和 tensorflow-lite 程式庫:

之前

implementation("com.google.firebase:firebase-ml-model-interpreter:22.0.1")

晚於

implementation("com.google.firebase:firebase-ml-model-interpreter:22.0.2")
implementation("org.tensorflow:tensorflow-lite:2.0.0")

2. 建立 TensorFlow Lite 解譯器,而非 FirebaseModelInterpreter

請勿建立 FirebaseModelInterpreter,而是使用 getLatestModelFile() 取得模型在裝置上的位置,並用來建立 TensorFlow Lite Interpreter

之前

Kotlin

val remoteModel = FirebaseCustomRemoteModel.Builder("your_model").build()
val options = FirebaseModelInterpreterOptions.Builder(remoteModel).build()
val interpreter = FirebaseModelInterpreter.getInstance(options)

Java

FirebaseCustomRemoteModel remoteModel =
        new FirebaseCustomRemoteModel.Builder("your_model").build();
FirebaseModelInterpreterOptions options =
        new FirebaseModelInterpreterOptions.Builder(remoteModel).build();
FirebaseModelInterpreter interpreter = FirebaseModelInterpreter.getInstance(options);

晚於

Kotlin

val remoteModel = FirebaseCustomRemoteModel.Builder("your_model").build()
FirebaseModelManager.getInstance().getLatestModelFile(remoteModel)
    .addOnCompleteListener { task ->
        val modelFile = task.getResult()
        if (modelFile != null) {
            // Instantiate an org.tensorflow.lite.Interpreter object.
            interpreter = Interpreter(modelFile)
        }
    }

Java

FirebaseCustomRemoteModel remoteModel =
        new FirebaseCustomRemoteModel.Builder("your_model").build();
FirebaseModelManager.getInstance().getLatestModelFile(remoteModel)
        .addOnCompleteListener(new OnCompleteListener<File>() {
            @Override
            public void onComplete(@NonNull Task<File> task) {
                File modelFile = task.getResult();
                if (modelFile != null) {
                    // Instantiate an org.tensorflow.lite.Interpreter object.
                    Interpreter interpreter = new Interpreter(modelFile);
                }
            }
        });

3. 更新輸入和輸出準備程式碼

使用 FirebaseModelInterpreter 時,您可以在執行解譯器時,將 FirebaseModelInputOutputOptions 物件傳遞至解譯器,藉此指定模型的輸入和輸出形狀。

如果是 TensorFlow Lite 解譯器,您要改為為模型的輸入和輸出分配適當大小的 ByteBuffer 物件。

舉例來說,如果模型的輸入形狀為 [1 224 224 3] float 值,輸出形狀為 [1 1000] float 值,請進行下列變更:

之前

Kotlin

val inputOutputOptions = FirebaseModelInputOutputOptions.Builder()
    .setInputFormat(0, FirebaseModelDataType.FLOAT32, intArrayOf(1, 224, 224, 3))
    .setOutputFormat(0, FirebaseModelDataType.FLOAT32, intArrayOf(1, 1000))
    .build()

val input = ByteBuffer.allocateDirect(224*224*3*4).order(ByteOrder.nativeOrder())
// Then populate with input data.

val inputs = FirebaseModelInputs.Builder()
    .add(input)
    .build()

interpreter.run(inputs, inputOutputOptions)
    .addOnSuccessListener { outputs ->
        // ...
    }
    .addOnFailureListener {
        // Task failed with an exception.
        // ...
    }

Java

FirebaseModelInputOutputOptions inputOutputOptions =
        new FirebaseModelInputOutputOptions.Builder()
                .setInputFormat(0, FirebaseModelDataType.FLOAT32, new int[]{1, 224, 224, 3})
                .setOutputFormat(0, FirebaseModelDataType.FLOAT32, new int[]{1, 1000})
                .build();

float[][][][] input = new float[1][224][224][3];
// Then populate with input data.

FirebaseModelInputs inputs = new FirebaseModelInputs.Builder()
        .add(input)
        .build();

interpreter.run(inputs, inputOutputOptions)
        .addOnSuccessListener(
                new OnSuccessListener<FirebaseModelOutputs>() {
                    @Override
                    public void onSuccess(FirebaseModelOutputs result) {
                        // ...
                    }
                })
        .addOnFailureListener(
                new OnFailureListener() {
                    @Override
                    public void onFailure(@NonNull Exception e) {
                        // Task failed with an exception
                        // ...
                    }
                });

晚於

Kotlin

val inBufferSize = 1 * 224 * 224 * 3 * java.lang.Float.SIZE / java.lang.Byte.SIZE
val inputBuffer = ByteBuffer.allocateDirect(inBufferSize).order(ByteOrder.nativeOrder())
// Then populate with input data.

val outBufferSize = 1 * 1000 * java.lang.Float.SIZE / java.lang.Byte.SIZE
val outputBuffer = ByteBuffer.allocateDirect(outBufferSize).order(ByteOrder.nativeOrder())

interpreter.run(inputBuffer, outputBuffer)

Java

int inBufferSize = 1 * 224 * 224 * 3 * java.lang.Float.SIZE / java.lang.Byte.SIZE;
ByteBuffer inputBuffer =
        ByteBuffer.allocateDirect(inBufferSize).order(ByteOrder.nativeOrder());
// Then populate with input data.

int outBufferSize = 1 * 1000 * java.lang.Float.SIZE / java.lang.Byte.SIZE;
ByteBuffer outputBuffer =
        ByteBuffer.allocateDirect(outBufferSize).order(ByteOrder.nativeOrder());

interpreter.run(inputBuffer, outputBuffer);

4. 更新輸出處理程式碼

最後,請勿使用 FirebaseModelOutputs 物件的 getOutput() 方法取得模型輸出內容,而是將 ByteBuffer 輸出內容轉換為適合您用途的結構。

舉例來說,如果您要進行分類,可以進行下列變更:

之前

Kotlin

val output = result.getOutput(0)
val probabilities = output[0]
try {
    val reader = BufferedReader(InputStreamReader(assets.open("custom_labels.txt")))
    for (probability in probabilities) {
        val label: String = reader.readLine()
        println("$label: $probability")
    }
} catch (e: IOException) {
    // File not found?
}

Java

float[][] output = result.getOutput(0);
float[] probabilities = output[0];
try {
    BufferedReader reader = new BufferedReader(
          new InputStreamReader(getAssets().open("custom_labels.txt")));
    for (float probability : probabilities) {
        String label = reader.readLine();
        Log.i(TAG, String.format("%s: %1.4f", label, probability));
    }
} catch (IOException e) {
    // File not found?
}

晚於

Kotlin

modelOutput.rewind()
val probabilities = modelOutput.asFloatBuffer()
try {
    val reader = BufferedReader(
            InputStreamReader(assets.open("custom_labels.txt")))
    for (i in probabilities.capacity()) {
        val label: String = reader.readLine()
        val probability = probabilities.get(i)
        println("$label: $probability")
    }
} catch (e: IOException) {
    // File not found?
}

Java

modelOutput.rewind();
FloatBuffer probabilities = modelOutput.asFloatBuffer();
try {
    BufferedReader reader = new BufferedReader(
            new InputStreamReader(getAssets().open("custom_labels.txt")));
    for (int i = 0; i < probabilities.capacity(); i++) {
        String label = reader.readLine();
        float probability = probabilities.get(i);
        Log.i(TAG, String.format("%s: %1.4f", label, probability));
    }
} catch (IOException e) {
    // File not found?
}