clarification on tube generation

[orikorner]

Hi, Regarding the tube generation process in get_mask() in evaluator.py.
As far as i can see the actor's bounding boxes are extracted using SiamMask on images of size 640x360 (FRFS) which are then passed to get_mask(). On the other hand the dataloader in get_imgs() first down scales frames to 455x256 followed by a crop of 224x224.
From looking at get_mask() i see that lines 21-25 intend to place the actor's bounding box properly on the feature maps (spatially), but i am not certain they will fit spatially because the actors bounding boxes did not adjust to the same downscale and crop process that the frames did.
Is this a bug or i perhaps i am misunderstanding something?
Thanks

[Shunli-Wang]

Thank you very much for pointing out our problems. We checked the code and found that we ignored this mismatch.

Since the data loading part of the code uses the CenterCrop operation, only the feature tube near the center of the image can be enhanced. The performance of the TSA module may be weakened by this implementation. We will update the code in the future and test the performance of the right TSA module.

Thank you for your contribution!

[UlisesGallardo]

Hi, Is there any alternative implementation available for this TSA module? Thank you.