Object detection stops predicting well according to how I collect the images

On my problem I have to use 4k resolution (3840×2160) to record images and detect qrcodes at the same time. The images I end resizing it to 1920×1080 to save it on disk.

The problem is that if I train using this resized data the model stops predicting well compared to when I record the video on native 1920×1080.
I can’t have good results nor if I predict with resized to 1920×1080 neither native 1920×1080 with this train.
If I train using native recorded at 1920×1080 it predicts well both with native 1920×1080 and resized 1920×1080.

Is there some explanation about why this is occurring?

I always try to save the images as jps with quality=95 and the camera I’m using compresses the image before sending to opencv (directly affects the fps).

I can’t go back to 1920×1080 because the qrcode reader stops detecting.

How I record the video without resize (working method):

for z, frame in enumerate(frames):
    try:
        self.out.write(cv2.cvtColor(frame2, cv2.COLOR_BGR2RGB))
    except AttributeError:
        self.out = cv2.VideoWriter(ANNOTATION_RECORD_VIDEO_FILE, cv2.VideoWriter_fourcc('m','p','4','v'), 60, (conf.cameras.phase1[0].resolution.width, conf.cameras.phase1[0].resolution.height))
        self.out.write(cv2.cvtColor(frame2, cv2.COLOR_BGR2RGB))

With resize (frames are coming with 4k res):

for z, frame in enumerate(frames):
    frame = cv2.resize(frame, dsize=(conf.annotation.resolution_to_save['width'], 
                                        conf.annotation.resolution_to_save['height']), 
                                interpolation=cv2.INTER_CUBIC)

    try:
        self.out.write(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
    except AttributeError:
        self.out = cv2.VideoWriter(ANNOTATION_RECORD_VIDEO_FILE, cv2.VideoWriter_fourcc('m','p','4','v'), 60, (conf.annotation.resolution_to_save['width'], conf.annotation.resolution_to_save['height']))
        self.out.write(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))