Hello everyone,
I used two yolov5 models.
My first model detects the tray. In my second model, it finds food types.
The size of the first model was 416, then I cropped it. I sent it to
the second model. The size of my second model is 224.
my question: There is a shift in the second model in the example_output.jpg
image. Second model failed to draw bounding boxes properly.I would love any advice.
Thank you very much.
Hi @Laura1 ,
First adjust the horizontal and vertical scaling factors and then offset the X , Y coordinates based on the center coordinates of the original image. Here is the sample code to adjust the coordinates. Please change according to your data structure.
# Apply scaling factors
if not normalized:
left *= scaling_factors[0]
top *= scaling_factors[1]
right *= scaling_factors[0]
bottom *= scaling_factors[1]
# Offset both X, Y coordinates by tray center
left += tray_center[0]
top += tray_center[1]
right += tray_center[0]
bottom += tray_center[1]
Thank You