I have a 4 dimensional float array of size [1][300][3][1] which I have to give as Input for a .tflite model built in python.
I tried converting the the 4D float array to a FloatBuffer using the below code.
FloatBuffer fb = FloatBuffer.allocate(1*300*3*1);
for (int i = 0; i < 1; i++)
{
for (int j = 0; j < 300; j++)
{
for (int k = 0; k < 3; k++)
{
for (int l = 0; l < 1; l++)
{
fb.put(inputData[i][j][k][l]);
}
}
}
}
float[][] outputData = new float[1][16];
tflite.run(fb,outputData);
I am able to get output but the iutput value is different when running it in python and with my Java code. Is the above code affecting the accuracy of the model?