OpenCV background subtraction learning rate cannot change

Question

I wish to train a background region with 50 frames and use this pre-trained model for background subtraction. Model stops updating after training.

Here is my code

import cv2
print "This program is for background subtraction with pre-trained model\n"

Training_Floder = "/Users/yuyang/Desktop/img1/"
Start_Frame_Num = 1
End_Frame_Num = 51

cv2.namedWindow("BG_IMAGE")

fgbg = cv2.createBackgroundSubtractorMOG2(50, 16, False)
font = cv2.FONT_HERSHEY_SIMPLEX



for index in range(Start_Frame_Num, End_Frame_Num):
    Img_File_Name = Training_Floder + str(index) + ".jpg"
    Img = cv2.imread(Img_File_Name)
    fgmask = fgbg.apply(Img, -1)
    BG_IMG = fgbg.getBackgroundImage()
    #######
    cv2.putText(BG_IMG,str(index),(10,500), font, 1,(255,255,255),2)
    cv2.imshow("BG_IMAGE", BG_IMG)
    #######
    cv2.waitKey(0)

Testing_Floder = "/Users/yuyang/Desktop/New/"
Test_Start = 1
Test_End = 100

for index in range(Test_Start, Test_End):
    Img_File_Name = Testing_Floder + str(index) + ".jpg"
    Img = cv2.imread(Img_File_Name)
    fgmask1 = fgbg.apply(Img, 0)
    BG_IMG1 = fgbg.getBackgroundImage()
    cv2.putText(BG_IMG1,str(index),(10,500), font, 1,(255,255,255),2)
    cv2.imshow("BG_IMAGE", BG_IMG1)
    cv2.waitKey(0)

Based on the comments

The learning rate parameter is in the function "apply()".

@param learningRate 
The value between 0 and 1 that indicates how fast the background 
model is learnt. Negative parameter value makes the algorithm to 
use some automatically chosen learning rate. 0 means that the 
background model is not updated at all, 1 means that the background 
model is completely reinitialized from the last frame.

CV_WRAP virtual void apply(InputArray image, OutputArray fgmask, double learningRate=-1) = 0;"

However, I tried several learning rate here:

fgmask = fgbg.apply(Img, -1) or
fgmask = fgbg.apply(Img, 0) or
fgmask = fgbg.apply(Img, 1) or
fgmask = fgbg.apply(Img, 0.00001)

The training Background result does not change. This means I CANNOT keep pre-trained model unchanged while testing!

Is there anything wrong with my code? Is there any way to change the learning rate?

Here are some results

Background subtraction result of Testing image #1

Background subtraction result of Testing image #40

From the result above, it is clear that the trained background image changes while testing, although I set learning rate as 0.

fgmask1 = fgbg.apply(Img, 0)

Answer 1

So the correct way to use the python implementation is

fgbg = cv2.createBackgroundSubtractorMOG2(50, 16, False)
fgbg.apply(input, output, learning_rate)

Exactly as in the c++ implementation. The learning rate must be the third parameter.