java - tflite implantation in android studio - fails to classify frame

Question

I'm working on a tflite project in android studio (in Java). I'm failing to run the line: String textToShow = imageClassifier.classifyFrame(bitmap); (getting an exception every time).

This is the ClassifyFrame function:

ImageClassifier(Activity activity) throws IOException {
        tflite = new Interpreter(loadModelFile(activity));
        labelList = loadLabelList(activity);
        imgData =
                ByteBuffer.allocateDirect(
                        DIM_BATCH_SIZE * DIM_IMG_SIZE_X * DIM_IMG_SIZE_Y * DIM_PIXEL_SIZE);
        imgData.order(ByteOrder.nativeOrder());
        labelProbArray = new float[1][labelList.size()];
        Log.d(TAG, "Created a Tensorflow Lite Image Classifier.");
    }

    /**
     * Classifies a frame from the preview stream.
     */
    String classifyFrame(Bitmap bitmap) {
        if (tflite == null) {
            Log.e(TAG, "Image classifier has not been initialized; Skipped.");
            return "Uninitialized Classifier.";
        }
        convertBitmapToByteBuffer(bitmap);
        // Here's where the magic happens!!!
        long startTime = SystemClock.uptimeMillis();


        int[] dimensions = new int[4];
        dimensions[0] = 1; // Batch_size // No of frames at a time
        dimensions[1] = 224; // Image Width required by model
        dimensions[2] = 224; // Image Height required by model
        dimensions[3] = 3; // No of Pixels
        //Tensor tensor = tflite.getInputTensor(0);
        tflite.resizeInput(0, dimensions);
        //Tensor tensor1 = tflite.getInputTensor(0);

        tflite.run(imgData, labelProbArray);
        long endTime = SystemClock.uptimeMillis();
        Log.d(TAG, "Timecost to run model inference: " + Long.toString(endTime - startTime));
        String textToShow = printTopKLabels();
        textToShow = Long.toString(endTime - startTime) + "ms" + textToShow;
        return textToShow;
    }

    /**
     * Reads label list from Assets.
     */
    private List<String> loadLabelList(Activity activity) throws IOException {
        List<String> labelList = new ArrayList<String>();
        BufferedReader reader =
                new BufferedReader(new InputStreamReader(activity.getAssets().open(LABEL_PATH)));
        String line;
        while ((line = reader.readLine()) != null) {
            labelList.add(line);
        }
        reader.close();
        return labelList;
    }

The output type for the model is float as recommended here to solve the problem: private float[][] labelProbArray = null;

This is the comment in the Logcut: E/OpenGLRenderer: ReliableSurface: perform returned an error

Would appreciate any help!

question from:https://stackoverflow.com/questions/66046558/tflite-implantation-in-android-studio-fails-to-classify-frame

Answer 1

Waitting for answers