I have noticed that Opencv imread was loading color channels in BGR order, what I did not know before. Since I suppose the original weights are made to deal with the channels in RGB order, I swapped the channels back by adding the line:
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
,at the beggining of the function process_image.
It indeed increased the detection rate especially for the yolo_tiny model. It may solve issue #8 btw.
eehoeskrap
commented
5 years ago
I have noticed that Opencv imread was loading color channels in BGR order, what I did not know before. Since I suppose the original weights are made to deal with the channels in RGB order, I swapped the channels back by adding the line:
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
,at the beggining of the function process_image.
It indeed increased the detection rate especially for the yolo_tiny model. It may solve issue #8 btw.