OrienHead in YoloMask for different backbones

[TeodorChiaburu]

Hi! While trying to train a YOLO-Mask with a Swin-Tiny backbone, I found out that the Overhead class in yolov7/modeling/meta_arch/yolomask.py requires a 4-dimensional input shape, while the Transformer only delivers 3d. There is also a todo marked in the comments on line 341 of the file. I tried it with a Darknet backbone and it worked. I assume ResNet would also work fine. Any tips on how we can expand this feature for transformers?

[lucasjinreal]

Hi, the OrienMaskHead essentially need same feature feed like detect head, normally provided 3 featuremaps in shape like [1,128,98,90], [1,256,49,45], [1,512,25, 22],

I didn't tried Swin so not very clear about it's outputs, but in if you able to make these 3 output features, you are able to feed to any YOLO head.