從舊版自訂模型 API 遷移

firebase-ml-model-interpreter 程式庫的 22.0.2 版推出了新的 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，以便取代 FirebaseModelInterpreter 包裝函式。

這將是我們日後偏好的做法。由於 TensorFlow Lite 解譯器版本不再與 Firebase 程式庫版本配對，因此您可以更靈活地在需要時升級至新版 TensorFlow Lite，或更輕鬆地使用自訂 TensorFlow Lite 版本。

本頁面說明如何從使用 FirebaseModelInterpreter 改為使用 TensorFlow Lite Interpreter。

1. 更新專案依附元件

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

早於

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 FirebaseModelTranslateer

請在以下位置取得模型的位置，而不要建立 FirebaseModelInterpreter 並用來建立 TensorFlow Lite getLatestModelFile() Interpreter。

早於

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

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

晚於

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)
        }
    }

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 即可指定模型的輸入和輸出形狀 方法是將 FirebaseModelInputOutputOptions 物件傳遞至解譯器 每個階段執行時

針對 TensorFlow Lite 解譯器，您應為模型的輸入和輸出分配大小適當的 ByteBuffer 物件。

舉例來說，如果模型的輸入形狀為 [1 224 224 3] float 值，而輸出形狀為 [1 1000] float 值，請進行以下變更：

早於

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.
        // ...
    }

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

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)

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，請不要使用 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，可能會進行下列變更：

早於

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?
}

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

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?
}

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?
}