Using SAM in VS Code · Data Alchemy

Using SAM in VS Code

In VS Code terminal:

cd segment-anything

pip install -r requirements.txt

2. Download Pre-Trained Model:

Get the .pth model from segment-anything.com and save it in a models folder.

3. Write a Script:

Create a use_sam.py file:

from segment_anything import SamPredictor, sam_model_registry

from PIL import Image

import numpy as np

sam = sam_model_registry["vit_b"](checkpoint="models/sam_vit_b.pth")

predictor = SamPredictor(sam)

image = np.array(Image.open("your_image.jpg"))

predictor.set_image(image)

masks, _, _ = predictor.predict(point_coords=np.array([[100, 200]]), point_labels=np.array([1]))

print(masks)

4. Run It:

In the terminal:

python use_sam.py

That’s it—start experimenting with SAM!

1 comment

skool.com/data-alchemy

Your Community to Master the Fundamentals of Working with Data and AI — by Datalumina®

Leaderboard (30-day)

+203

+75

+33

+32

+28