为什么 tflite 模型的准确性与 keras 模型如此不同? [英] Why accuracy of tflite model is so different from keras model?

问题描述

我制作了一个模型来预测图像上的字符，以进行车牌识别.它在我的电脑上运行良好，但我需要将这项工作放在 Android 应用程序中.所以我开发了一个小应用程序并将我的 keras 模型转换为 tflite.现在它总是预测相同的字符.

I made a model that predict a character on an image, to do license plate recognition. It works very well on my computer, but I need to put this work in an Android app. So I developped a little application and convert my keras model to tflite. And now it's always predicting the same character.

我使用以下方法转换模型:

I converted the model using :

mod_path = "License_character_recognition.h5"

def load_model(path,custom_objects={},verbose=0):
    #from tf.keras.models import model_from_json

    path = splitext(path)[0]
    with open('MobileNets_character_recognition.json','r') as json_file:
        model_json = json_file.read()
    model = tf.keras.models.model_from_json(model_json, custom_objects=custom_objects)
    model.load_weights('%s.h5' % path)
    if verbose: print('Loaded from %s' % path)
    return model

keras_mod = load_model(mod_path)

converter = tf.lite.TFLiteConverter.from_keras_model(keras_mod)
tflite_model = converter.convert()

# Save the TF Lite model.
with tf.io.gfile.GFile('ocr.tflite', 'wb') as f:
    f.write(tflite_model)

有没有更好的方法来转换模型，还是我遗漏了什么?

Is there a better way to convert the model, or am I missing something ?

这就是我为管理位图所做的

EDIT : This is what I did to manage the bitmap

        try {
            Mat bis = Utils.loadResource(MainActivity.this, R.drawable.plaque, Imgcodecs.IMREAD_COLOR);
            cvtColor(bis, bis, COLOR_BGR2RGB);

            Mat m = Utils.loadResource(MainActivity.this, R.drawable.plaque,Imgcodecs.IMREAD_GRAYSCALE);

            blur(m, blur, new Size(2,2));

            threshold(blur, bin, 0, 255, THRESH_BINARY_INV + THRESH_OTSU);

            ArrayList<MatOfPoint> contours;
            contours = getContours(bin);

            //Try to sort from left to right
            Collections.sort(contours, new SortByTopLeft());
            Log.d("Contour", String.valueOf(contours.size()));
            int i = 0;
            for (MatOfPoint c : contours){
                Rect cont = boundingRect(c);
                float ratio = (float) (cont.height/cont.width);
                Log.d("Ratio", String.valueOf(ratio));
                float pourcent =  ((float) cont.height/ (float) bin.height());
                Log.d("pourcent", String.valueOf(pourcent));
                if (ratio >= 1 && ratio <= 2.5){
                    if(pourcent >=0.5){
                        Log.d("Ui", String.valueOf(cont));
                        rectangle(bis, cont, new Scalar(0,255,0), 2);

                        //Separate numbers
                        Mat curr_num = new Mat(bin, cont);
                        Bitmap curbit = Bitmap.createBitmap(curr_num.cols(), curr_num.rows(), Bitmap.Config.ARGB_8888);
                        Utils.matToBitmap(curr_num, curbit);
                        images[i].setImageBitmap(curbit);
                        int charac = classifier.classify(curbit);
                        Log.d("Result", String.valueOf(charac));
                        result.setText(String.valueOf(charac));
                        if (i < 6){
                            i++;
                        }
                    }

                }

推荐答案

您可以使用 TensorFlow Lite Android 支持库.这个库旨在帮助处理输入和输出TensorFlow Lite 模型，并使 TensorFlow Lite 解释器更易于使用.

You can use TensorFlow Lite Android Support Library. This library is designed to help process the input and output of TensorFlow Lite models, and make the TensorFlow Lite interpreter easier to use.

像下面一样使用它并在 这篇文章:

Use it like below and find more at this article:

    Bitmap assetsBitmap = getBitmapFromAsset(mContext, "picture.jpg");
    // Initialization code
    // Create an ImageProcessor with all ops required. For more ops, please
    // refer to the ImageProcessor Architecture.
    ImageProcessor imageProcessor =
            new ImageProcessor.Builder()
                    .add(new ResizeOp(32, 32, ResizeOp.ResizeMethod.BILINEAR))
                    //.add(new NormalizeOp(127.5f, 127.5f))
                    .build();

    // Create a TensorImage object. This creates the tensor of the corresponding
    // tensor type (flot32 in this case) that the TensorFlow Lite interpreter needs.
    TensorImage tImage = new TensorImage(DataType.FLOAT32);

    // Analysis code for every frame
    // Preprocess the image
    tImage.load(assetsBitmap);
    tImage = imageProcessor.process(tImage);

    // Create a container for the result and specify that this is not a quantized model.
    // Hence, the 'DataType' is defined as FLOAT32
    TensorBuffer probabilityBuffer = TensorBuffer.createFixedSize(new int[]{1, 10}, DataType.FLOAT32);
    interpreter.run(tImage.getBuffer(), probabilityBuffer.getBuffer());

    Log.i("RESULT", Arrays.toString(probabilityBuffer.getFloatArray()));

    return getSortedResult(result);
}

这篇关于为什么 tflite 模型的准确性与 keras 模型如此不同?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！