從舊版自訂模型 API 遷移

firebase-ml-model-interpreter 程式庫 22.0.2 版引進了全新功能 getLatestModelFile() 方法，可取得自訂裝置上的位置資訊 我們來看評估分類模型成效時 的喚回度和精確度指標您可以使用這個方法直接將 TensorFlow Lite 執行個體化 Interpreter 物件，您可以使用該物件取代 FirebaseModelInterpreter 包裝函式。

這也是我們建議日後的方法。由於 TensorFlow Lite 翻譯版本不再與 Firebase 程式庫版本結合， 也能更靈活地升級至新版 TensorFlow Lite 或更輕鬆地自訂 TensorFlow Lite 版本

本頁說明如何從使用 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 22.0.2 版 firebase-ml-model-interpreter 程式庫 (或更新版本) 和 tensorflow-lite 程式庫：

更新前

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

更新後

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 LitegetLatestModelFile() Interpreter。

更新前

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);

更新後

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

使用 TensorFlow Lite 解譯器，請改為分配 ByteBuffer 物件 為模型輸入和輸出正確大小

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

更新前

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
                        // ...
                    }
                });

更新後

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，而不是使用 FirebaseModelOutputs 取得模型的輸出內容 物件的 getOutput() 方法，將 ByteBuffer 輸出內容轉換為 方便您達成目標

舉例來說，如果要分類，您可能會進行 包括：

更新前

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?
}

更新後

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?
}