Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Difficulties using Object segmentations with FastSAM and OpenVINO #2482

Open
D10123 opened this issue Oct 28, 2024 · 1 comment
Open

Difficulties using Object segmentations with FastSAM and OpenVINO #2482

D10123 opened this issue Oct 28, 2024 · 1 comment
Assignees

Comments

@D10123
Copy link

D10123 commented Oct 28, 2024

I am trying to use the OpenVINO model without first loading the FastSAM model (thus, I only need to use the OpenVINO one).
To do that, I directly loaded the model and used ov.compile_model() to initialize it. Also, I am not using the OVwrapper class.
I am now trying to apply the function segment() on this model but I do not understand how I need to manipulate the input data and how to modify the segment function for it to work. Does anyone know where I can find this information in the documentation?

@Wan-Intel
Copy link

Wan-Intel commented Oct 29, 2024

You may modify the function below that is called to segment an image based on user input.

def segment(
    image,
    model_type,
    input_size=1024,
    iou_threshold=0.75,
    conf_threshold=0.4,
    better_quality=True,
    with_contours=True,
    use_retina=True,
    mask_random_color=True,
)

For more information, please refer to Object segmentations with FastSAM and OpenVINO

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants