android - tflite.run() returning same output for different input values
问题描述
I am trying to make an android app for monument recognition. The input changes on every run but output returned is always same.
Below are the code snippets
to load tflite model stored in assets directory
private ByteBuffer loadModelFile(String filename) throws IOException {
AssetFileDescriptor fileDescriptor = this.getAssets().openFd(filename);
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);
}
to initialize tflite interpreter
predict.setOnClickListener(new View.OnClickListener() {
@RequiresApi(api = Build.VERSION_CODES.O)
@Override
public void onClick(View v) {
try {
tflite = new Interpreter(loadModelFile("converted_model.tflite"));
Log.println(7,"tflite", "tflite init");
doInference(picFile);
} catch (Exception e) {
System.out.println(e);
}
}
});
to run the model
@RequiresApi(api = Build.VERSION_CODES.O)
public void doInference(File photo) throws IOException {
img = findViewById(R.id.imgToDisp);
Bitmap bitmapImg = BitmapFactory.decodeFile(pathToFile);
img.setImageBitmap(bitmapImg);
ByteArrayOutputStream stream = new ByteArrayOutputStream();
bitmapImg.compress(Bitmap.CompressFormat.JPEG, 50, stream);
byte[] arr = stream.toByteArray();
changedim = new float[1][150][150][3];
outputval = new float[1][28];
int m = 0;
for (int i = 0; i < 1; i++) {
for (int j = 0; j < 150; j++) {
for (int k = 0; k < 150; k++) {
for (int l = 0; l < 3; l++) {
byte a = arr[m++];
changedim[i][j][k][l] = Byte.toUnsignedLong(a);
}
}
}
}
tflite.run(changedim, outputval);
for(int i=0;i<28;i++) {
Log.println(7,"outputval",i+" "+outputval[0][i]);
}
path = findViewById(R.id.path);
String out = "";
float[] op = outputval[0];
int ind = 0;
float max = op[0];
while (op[ind] != 1) {
ind++;
//Log.println(7,"op", " "+op[ind]+" "+ind);
}
for (float f : op) {
out += Float.toString(f) + ",";
}
predict.setText("result: " + labels.get(ind));
Log.println(7, "label", ind + " " + labels.get(ind));
//path.setText(""+pathToFile);
}
input to the model must be an image of size 150*150 converted to 4d float32 array of shape 1*150*150*3
解决方案
Input to the model is the color values of individual pixels. Which can be extracted using
int p = bitmapImg.getPixel(j, k);
int R = (p >> 16) & 0xff;
int G = (p >> 8) & 0xff;
int B = p & 0xff;
change that and your model will work correctly!
推荐阅读
- python - 从 TensorFlow 2.x 降级到 1.15
- python - 我正在寻找一个不使用循环将整数 X 映射到 0.X 的函数
- ios - 如何在 SwiftUI 中制作屏幕高度一半的图像?
- dictionary - Kotlin可变映射中的增量元素
- nginx - 使用 nginx 从另一台服务器设置 Web 服务器复制响应
- python - ANSI 转义颜色代码在 Python 终端中不起作用
- javascript - 为什么我不能使用填充访问 mongoose 对象的子字段?
- c++ - C++ 读取内存失败
- typescript - 推送到 TypeScript 中的嵌套数组
- google-sheets - 在 Google 表格中定义命名范围时可以跳过范围吗?