-
Notifications
You must be signed in to change notification settings - Fork 911
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
It’s GroundedSAM free or not? #277
Comments
I'm not sure if this repository is the best place for this ticket. I recommend moving it to autodistill. To answer your question, the |
Yes. I need to use it without internet in my project. If i using autodistill-grounded-sam and download model to my computer work station. That mean i can using this code without API key anymore? |
@Siwakonrome, Once the model is cached, you don't need the internet anymore. |
My project cannot connect internet after deployed it on production. Thanks for your information. |
I'm closing the issue :) |
Search before asking
Description
It’s GroundedSAM free or not? If not How to get Api key to using this service?
import cv2
import supervision as sv
from autodistill_grounded_sam import GroundedSAM
from autodistill.detection import CaptionOntology
class GroundedSAMOperator:
def init(self, caption):
self.caption = caption
self.base_model = GroundedSAM(ontology=CaptionOntology(self.caption))
self.classes = base_model.ontology.classes()
def call(self, image):
detections = self.base_model.predict(image)
labels = [f"{self.classes[class_id]} {confidence:0.2f}" for _, _, confidence, class_id, _ in detections]
print(labels)
return detections
image = cv2.imread("/content/aluminum.jpg")
caption = { "aluminum workpiece": "aluminum" }
grounded_sam_operator = GroundedSAMOperator(caption)
detections = grounded_sam_operator(image)
mask_annotator = sv.MaskAnnotator()
annotated_frame = mask_annotator.annotate(
scene=image.copy(),
detections=detections)
sv.plot_image(annotated_frame, size=(8, 8))
Additional
No response
Are you willing to submit a PR?
The text was updated successfully, but these errors were encountered: