FirebaseModelInterpreter

Interpreter to run custom models with TensorFlow Lite (requires API level 16+)

A model interpreter is created via getInstance(FirebaseModelOptions). Follow the steps below to specify the FirebaseModelOptions, create a FirebaseModelInterpreter and all the way to running an inference with the model.

Firstly, create at least one of FirebaseCloudModelSource and FirebaseLocalModelSource, and register them with FirebaseModelManager. Note that the FirebaseCloudModelSource has higher precedence, which means the FirebaseLocalModelSource will only be used if there is no FirebaseCloudModelSource or the download of FirebaseCloudModelSource fails. It is recommended to specify both local and cloud model source in case the download of FirebaseCloudModelSource fails or the internet is slow.

The following code creates and registers the model sources:

 FirebaseModelManager.getInstance()
  .registerCloudModelSource(
      new FirebaseCloudModelSource.Builder(cloudModelName)
          .setInitialDownloadConditions(initialConditions)
          .setUpdatesDownloadConditions(updateConditions)
          .build());

 FirebaseModelManager.getInstance()
  .registerLocalModelSource(
      new FirebaseLocalModelSource.Builder(localModelName)
          .setFilePath(localModelFilePath)
          .build());

 FirebaseModelOptions modelOptions =
    new FirebaseModelOptions.Builder()
        .setCloudModelName(cloudModelName)
        .setLocalModelName(localModelName)
        .build();
 

Secondly, create an instance of FirebaseModelInterpreter with the FirebaseModelOptions.

 FirebaseModelInterpreter interpreter = FirebaseModelInterpreter.getInstance(modelOptions);
 

Thirdly, create a FirebaseModelInputs and a FirebaseModelInputOutputOptions. You need to know the input and output data specifications of the model, including the data types and input/output dimensions. The following code is an example:

 FirebaseModelInputs modelInputs = new FirebaseModelInputs.Builder().add(...).build();

 FirebaseModelInputOutputOptions inputOutputOptions =
     new FirebaseModelInputOutputOptions.Builder()
         .setInputFormat(0, FirebaseModelDataType.FLOAT32, inputDims)
         .setOutputFormat(0, FirebaseModelDataType.FLOAT32, outputDims)
         .build();
 

Lastly, feed the inputs to run(FirebaseModelInputs, FirebaseModelInputOutputOptions). The following code is an example:

 Task<FirebaseModelOutputs> task = interpreter.run(modelInputs, inputOutputOptions);
 task.addOnSuccessListener(...).addOnFailureListener(...);