Vibe Coding Discoversegment-anything
View on GitHubThe repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Meta's Segment Anything (SAM) is a vision foundation model that produces high-quality object masks from point/box prompts or fully automatic generation. The repo ships PyTorch inference code, checkpoint links, ONNX export, notebooks and a web demo.
Use Cases
Generate object masks from point or box promptsAutomatically segment all objects in an imageExport mask decoder to ONNX for in-browser inferenceBuild image editing and cutout pipelinesCreate training data via mask annotationZero-shot segmentation on arbitrary images
Built With
- Language
- Jupyter Notebook
- Frameworks
- PyTorch · TorchVision · ONNX Runtime · OpenCV · pycocotools · Matplotlib · React · Tailwind CSS
Tags
image-segmentation · computer-vision · foundation-model · sam · promptable-segmentation · mask-generation · zero-shot · pytorch · onnx · vit · inference · checkpoints · vision