Google 致力于为黑人社区推动种族平等。查看具体举措
此页面由 Cloud Translation API 翻译。
Switch to English

从旧的自定义模型API迁移

firebase firebase-ml-model-interpreter getLatestModelFile() firebase-ml-model-interpreter库的getLatestModelFile()引入了新的getLatestModelFile()方法,该方法获取自定义模型在设备上的位置。您可以使用此方法直接实例化TensorFlow Lite Interpreter对象,可以使用该对象代替FirebaseModelInterpreter包装器。

展望未来,这是首选方法。由于TensorFlow Lite解释器版本不再与Firebase库版本一起使用,因此您可以在需要时具有更大的灵活性来升级到TensorFlow Lite的新版本,或者更轻松地使用自定义TensorFlow Lite构建。

此页面显示了如何从使用FirebaseModelInterpreter迁移到TensorFlow Lite Interpreter

1.更新项目依赖项

更新项目的依赖项,以包括firebase firebase-ml-model-interpreter库(或更高版本)的tensorflow-litetensorflow-lite库:

之前

implementation 'com.google.firebase:firebase-ml-model-interpreter:22.0.1'

implementation 'com.google.firebase:firebase-ml-model-interpreter:22.0.2'
implementation 'org.tensorflow:tensorflow-lite:2.0.0'

2.创建一个TensorFlow Lite解释器,而不是FirebaseModelInterpreter

无需创建FirebaseModelInterpreter ,而是使用getLatestModelFile()获取模型在设备上的位置,然后使用它来创建TensorFlow Lite Interpreter

之前

爪哇

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

Kotlin + KTX

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

爪哇

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);
                }
            }
        });

Kotlin + KTX

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)
        }
    }

3.更新输入和输出准备代码

使用FirebaseModelInterpreter ,您可以通过在运行模型时将FirebaseModelInputOutputOptions对象传递给解释器来指定模型的输入和输出形状。

对于TensorFlow Lite解释器,您可以为模型的输入和输出分配大小合适的ByteBuffer对象。

例如,如果模型的输入形状为[1 224 224 3] float值,输出形状为[1 1000] float值,请进行以下更改:

之前

爪哇

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
                        // ...
                    }
                });

Kotlin + KTX

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.
        // ...
    }

爪哇

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);

Kotlin + KTX

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)

4.更新输出处理代码

最后,不要使用FirebaseModelOutputs对象的getOutput()方法获取模型的输出,而是将ByteBuffer输出转换为适合您的使用情况的任何结构。

例如,如果您要进行分类,则可以进行如下更改:

之前

爪哇

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?
}

Kotlin + KTX

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?
}

爪哇

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?
}

Kotlin + KTX

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?
}