Incorrect order of the box coordinates

[Laughing-q]

The order of the box coordinates should be xyxy instead of yxyx, the coordinates are split in the yxyx order but then stack the y_bb in xyxy order. https://github.com/sony/model_optimization/blob/173ed446146f62a119d5bf09b09ef6e49d27a138/tutorials/mct_model_garden/models_pytorch/yolov8/yolov8.py#L269-L272 https://github.com/sony/model_optimization/blob/173ed446146f62a119d5bf09b09ef6e49d27a138/tutorials/mct_model_garden/models_pytorch/yolov8/yolov8.py#L273 However with this incorrect order the quantization works well hence I suspect the mct package is also doing job with the incorrect yxyx order. We might need some updates on this point, then we could directly return the bounding boxes by y_bb.transpose(1, 2) instead of splitting first then stack if we could fix the order.

return y_bb.transpose(1, 2), y_cls

[Laughing-q]

@Idan-BenAmi Hey, could you also take a look at this issue? is there a way to fix the order of box coordinates to make sure it's consistent to ultralytics package's xyxy? which would help us to simplify the code a lot. Thanks!

[Idan-BenAmi]

Hey @Laughing-q, Just to confirm, in our adjusted model, the "Detect" class outputs the bounding box (y_bb) in the yxyx order, and you’re asking it to be in the xyxy order instead?

[Laughing-q]

@Idan-BenAmi yes! :) then it'd be consistent with our package.

[Idan-BenAmi]

Hi @Laughing-q, For xyxy modification please follow: PR you will also need to update the export code: https://github.com/ambitious-octopus/model_optimization/blob/main/ultralytics-exports/vanilla-yolo.py#L132

output_resize = {'shape': (INPUT_RESOLUTION, INPUT_RESOLUTION), 'aspect_ratio_preservation': True, 'normalized_coords': False, 'xyxy_bbox_format': True}

[Laughing-q]

@Idan-BenAmi It works! Thank you! @ambitious-octopus I'll push a update to ultralytics@quan to simplify the code a bit. :)

return y_bb.transpose(1, 2), y_cls