facebookresearch / facebookresearch/segment-anything
how to encode image same as like sam demo?
Open
- Dominant language
- Jupyter Notebook
- Stars
- 54.9k
- Forks
- 6.4k
- PR merge metrics
- No merged PRs in 30d
Description
i am doing like this..but not getting mask
image = cv2.imread(file_location)
predictor.set_image(image)
image_embedding = predictor.get_image_embedding().cpu().numpy().tobytes()
encoded=[base64.b64encode(image_embedding).decode('ascii')]
Contributor guide
Research direction
Compare the reported cv2.imread, predictor.set_image, get_image_embedding, and base64 encoding steps with the SAM demo notebook. Start by checking how the demo represents images and masks, then determine which expected output is missing before defining a fix.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- opencv, python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100