Thank you very much for sharing such a great work.
I was checking the paper and found few interesting models in the paper but pre-trained weights are not available here to try.
Swin-base camera only input models with input image size of 512x1408.
The available weights on the repo is: Swin-Base C+D on 512x1408. Are both same models?
Can the above model be used for inference with only Camera image data?
Thank you very much for sharing such a great work.
I was checking the paper and found few interesting models in the paper but pre-trained weights are not available here to try.
Swin-base camera only input models with input image size of 512x1408.
The available weights on the repo is: Swin-Base C+D on 512x1408. Are both same models?
Can the above model be used for inference with only Camera image data?