autodistill-grounded-sam-2
autodistill-grounded-sam-2 copied to clipboard
autodistill
Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.
i noticed that you add a bias by prefixing each prompt with "a photo of ", this is not what the normal user expects. please remove it as this is...
https://imgur.com/a/jIxYTMf Added the ability to track objects over time with SAM2 and grounding DINO, the idea of it from IDEA-Research Grounded SAM implementation.
I was trying to run some examples but apparently GPU with 8GB of memory is not enough. When I checked the code of the package I noticed that there is...
Hi! is this already in a usable state? I've installed it with `pip3 install autodistill-grounded-sam-2 autodistill-yolov8` trying the sample code from the readme results in: ``` from autodistill_grounded_sam_2 import GroundedSAM2...
When I call on GroundedSAM2 with the ontology, it reinstalls SAM2 every time I run the program. Is there some sort of flag I can set that would stop that...
`isdir` is not supposed to be used with `~`: ``` >>> os.isdir("~/.cache") False >>> ``` It needs to be expanded to the user: https://github.com/autodistill/autodistill-grounded-sam-2/blob/d6eebed1c9fda3cb0a1bf5aba3773467ce1deb54/autodistill_grounded_sam_2/helpers.py#L73-L75 and you already did in some...
When I installed Autostill-grounded-sam2, I am facing on the following questions: **1) It seems that the installation of SAM2 will be implemented every time when I run the python script.**...
Metadata
Owner
Metadata
Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.