Intelligent Mobile Projects with TensorFlow

Using the advanced GAN model

The runPix2PixBlurryModel method is similar to the code in the previous chapters where we used an image input to feed into our models. We first get the RGB values from the image bitmap and save them to a float array:

void runPix2PixBlurryModel() {    int[] intValues = new int[WANTED_WIDTH * WANTED_HEIGHT];    float[] floatValues = new float[WANTED_WIDTH * WANTED_HEIGHT * 3];    float[] outputValues = new float[WANTED_WIDTH * WANTED_HEIGHT * 3];    try {        Bitmap bitmap = BitmapFactory.decodeStream(getAssets().open(IMAGE_NAME));        Bitmap scaledBitmap = Bitmap.createScaledBitmap(bitmap, WANTED_WIDTH, WANTED_HEIGHT, true); scaledBitmap.getPixels(intValues, 0, scaledBitmap.getWidth(), 0, 0, scaledBitmap.getWidth(), scaledBitmap.getHeight()); ...