CODEWITHSUNDEEP
androidtensorflowandroid-gradle-plugintensorflow-lite
Lalit Sharma
Lalit Sharma

Reputation: 1150

converted_model.tflite does not encode a valid TensorFlowLite model: Could not open file_path. The model is not a valid Flatbuffer file

I am trying to load converted_tflite.tflite from the assets directory.
It's giving me an error java.lang.IllegalArgumentException: Contents of /file:/android_asset/converted_model.tflite does not encode a valid TensorFlowLite model: Could not open '/file:/android_asset/converted_model.tflite'.The model is not a valid Flatbuffer file

File file = new File("file:///android_asset/converted_model.tflite");
        try (Interpreter interpreter = new Interpreter(file)) {
            interpreter.run(inputData, output);
            Log.d("TF LOG", output);
        }catch(Exception e){
            e.printStackTrace();
}

What I tried based on the stackoverflow answers

aaptOptions {
    noCompress "tflite"
}

tensoflow-lite nighty version

implementation 'org.tensorflow:tensorflow-lite:0.1.2-nightly'

Upvotes: 0

Views: 5854

Answers (3)

Harish Babu
Harish Babu

Reputation: 341

Adding to the existing answers, if you have created the tflite model with latest Tensorflow version (2.4.0) and facing a similar issue, add the below line to dependencies of build.gradle file

implementation 'org.tensorflow:tensorflow-lite:2.4.0'

and use the function provided by @LalitSharma for loading the model from 'assets' directory.

Can find the most recent release here https://bintray.com/google/tensorflow/tensorflow-lite

Upvotes: 0

Lalit Sharma
Lalit Sharma

Reputation: 1150

I used tensorflow-nighty build gradle version 0.1.2

    implementation 'org.tensorflow:tensorflow-lite:0.1.2-nightly'

To load the model

/** Memory-map the model file in Assets. */
private static MappedByteBuffer loadModelFile(AssetManager assets, String modelFilename)
        throws IOException {
    AssetFileDescriptor fileDescriptor = assets.openFd(modelFilename);
    FileInputStream inputStream = new FileInputStream(fileDescriptor.getFileDescriptor());
    FileChannel fileChannel = inputStream.getChannel();
    long startOffset = fileDescriptor.getStartOffset();
    long declaredLength = fileDescriptor.getDeclaredLength();
    return fileChannel.map(FileChannel.MapMode.READ_ONLY, startOffset, declaredLength);
}

Upvotes: 2

Krunal V
Krunal V

Reputation: 1253

As error indicates model is not a valid Flatbuffer file. In your implementation, model is as a File. It supposed to be convert to flatbuffer file as implemented below,

FileInputStream f_input_stream= new FileInputStream(new File("file:///android_asset/converted_model.tflite"));
FileChannel f_channel = f_input_stream.getChannel();
MappedByteBuffer tflite_model = f_channel.map(FileChannel.MapMode.READ_ONLY, 0, f_channel .size());

And than you can use this tflite_model to create tflite interpreter as New Interpreter(...).

Upvotes: 1

Related Questions