Skip to content

kadirnar/segment-anything-video

Repository files navigation

MetaSeg: Packaged version of the Segment Anything repository

teaser
downloads HuggingFace Spaces

Package version Download Count Supported Python versions Project Status pre-commit.ci

This repo is a packaged version of the segment-anything model.

Installation

pip install metaseg

Usage

from metaseg import SegAutoMaskPredictor, SegManualMaskPredictor

# If gpu memory is not enough, reduce the points_per_side and points_per_batch.

# For image
results = SegAutoMaskPredictor().image_predict(
    source="image.jpg",
    model_type="vit_l", # vit_l, vit_h, vit_b
    points_per_side=16,
    points_per_batch=64,
    min_area=0,
    output_path="output.jpg",
    show=True,
    save=False,
)

# For video
results = SegAutoMaskPredictor().video_predict(
    source="video.mp4",
    model_type="vit_l", # vit_l, vit_h, vit_b
    points_per_side=16,
    points_per_batch=64,
    min_area=1000,
    output_path="output.mp4",
)

# For manuel box and point selection

# For image
results = SegManualMaskPredictor().image_predict(
    source="image.jpg",
    model_type="vit_l", # vit_l, vit_h, vit_b
    input_point=[[100, 100], [200, 200]],
    input_label=[0, 1],
    input_box=[100, 100, 200, 200], # or [[100, 100, 200, 200], [100, 100, 200, 200]]
    multimask_output=False,
    random_color=False,
    show=True,
    save=False,
)

# For video

results = SegManualMaskPredictor().video_predict(
    source="video.mp4",
    model_type="vit_l", # vit_l, vit_h, vit_b
    input_point=[0, 0, 100, 100],
    input_label=[0, 1],
    input_box=None,
    multimask_output=False,
    random_color=False,
    output_path="output.mp4",
)

SAHI + Segment Anything

pip install sahi metaseg
from metaseg.sahi_predict import SahiAutoSegmentation, sahi_sliced_predict

image_path = "image.jpg"
boxes = sahi_sliced_predict(
    image_path=image_path,
    detection_model_type="yolov5",  # yolov8, detectron2, mmdetection, torchvision
    detection_model_path="yolov5l6.pt",
    conf_th=0.25,
    image_size=1280,
    slice_height=256,
    slice_width=256,
    overlap_height_ratio=0.2,
    overlap_width_ratio=0.2,
)

SahiAutoSegmentation().image_predict(
    source=image_path,
    model_type="vit_b",
    input_box=boxes,
    multimask_output=False,
    random_color=False,
    show=True,
    save=False,
)

teaser

FalAI(Cloud GPU) + Segment Anything

pip install metaseg fal_serverless
fal-serverless auth login
# For Auto Mask
from metaseg import falai_automask_image

image = falai_automask_image(
    image_path="image.jpg",
    model_type="vit_b",
    points_per_side=16,
    points_per_batch=32,
    min_area=0,
)
image.show() # Show image
image.save("output.jpg") # Save image

# For Manual Mask
from metaseg import falai_manuelmask_image

image = falai_manualmask_image(
    image_path="image.jpg",
    model_type="vit_b",
    input_point=[[100, 100], [200, 200]],
    input_label=[0, 1],
    input_box=[100, 100, 200, 200], # or [[100, 100, 200, 200], [100, 100, 200, 200]],
    multimask_output=False,
    random_color=False,
)
image.show() # Show image
image.save("output.jpg") # Save image

Extra Features

  • Support for Yolov5/8, Detectron2, Mmdetection, Torchvision models
  • Support for video and web application(Huggingface Spaces)
  • Support for manual single multi box and point selection
  • Support for pip installation
  • Support for SAHI library
  • Support for FalAI