You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Yes, the input size of the model is 10241024. The images were processed using ResizeLongestSide-1024 in the original SAM project. In order to avoid tensorrt's dynamic inference of orig_img_size, the input size is fixed at 10241024. You can resize the output mask result to the original size of the image.
Does this algorithm process 1024x1024 ,no matter what size picture it processes ,Is the output image also that large?
The text was updated successfully, but these errors were encountered: