SKILLoptionalHermes Optional Skills

Segment Anything Model

Name: Segment Anything Model
Author: Orchestra Research

SAM: zero-shot image segmentation via points, boxes, masks

MultimodalImage SegmentationComputer VisionSAMZero-ShotOptionalHermes skill

Last registry verification2026-08-18v1.0.0Orchestra Research

Open original source ↗اقرأ بالعربية

Plain meaning

What does it add to Hermes?

SAM: zero-shot image segmentation via points, boxes, masks

Segment Anything Model is a skill related to files and documents. It can let the agent read, organize, or create documents within the folder or account scope you grant.

This plain-language explanation is based on the publisher description. The original text remains visible for verification.

Use it when

Use it when your goal in files and documents is clear and you can limit it to the data and actions it actually needs.

Skip it when

Do not add it merely to experiment when Hermes already has a simpler path, or when you cannot review its source and permissions.

Who is it for?

Best for users who want a repeatable way of working inside Hermes.

Safe first test

Use a test folder containing copies of non-sensitive files and begin with one read operation.

Original publisher description

SAM: zero-shot image segmentation via points, boxes, masks

✓

Data source

This entry was indexed from Hermes Optional Skills. Our explanation interprets the type and domain without inventing a capability not present upstream.

Security review

The source is official or editorially reviewed, but you still need to review permissions and version compatibility.

Safe setup path

Inspect, install, then test.

01
Open the source
Match the publisher, license, and description to your need. Check the real update history.
02
Review permissions and secrets
Never paste a secret value into this site. Use environment-variable names and grant the smallest scope.
03
Copy setup only after review
The controls below copy text. They do not execute commands on your device.
04
Test with a non-sensitive task
Inspect the visible tools, then exclude write or delete tools you do not need.

Install command

Review the command, then copy it.

hermes skills install segment-anything-model

Hermes Belarabi does not execute this command. Installation happens on your device and remains subject to Hermes scanning and your review.

The full skill definition

Exactly what Hermes loads when this skill runs.

Reproduced from the official documentation. Read it before enabling the skill: this text becomes the agent's instructions.

SAM: zero-shot image segmentation via points, boxes, masks.

Skill metadata

A lookup table. Do not read it all; find the row that applies to you.

Source	Optional — install with `hermes skills install official/mlops/segment-anything-model`
Path	`optional-skills/mlops/models/segment-anything-model`
Version	`1.0.0`
Author	Orchestra Research
License	MIT
Dependencies	`segment-anything`, `transformers>=4.30.0`, `torch>=1.7.0`
Platforms	linux, macos, windows
Tags	`Multimodal`, `Image Segmentation`, `Computer Vision`, `SAM`, `Zero-Shot`

Reference: full SKILL.md

Explains the idea itself. Read it slowly; the later sections build on it.

Guide to using Meta AI's Segment Anything Model for zero-shot image segmentation.

When to use SAM

Explains the idea itself. Read it slowly; the later sections build on it.

Use SAM when:

Need to segment any object in images without task-specific training
Building interactive annotation tools with point/box prompts
Generating training data for other vision models
Need zero-shot transfer to new image domains
Building object detection/segmentation pipelines
Processing medical, satellite, or domain-specific images

Key features:

Zero-shot segmentation: Works on any image domain without fine-tuning
Flexible prompts: Points, bounding boxes, or previous masks
Automatic segmentation: Generate all object masks automatically
High quality: Trained on 1.1 billion masks from 11 million images
Multiple model sizes: ViT-B (fastest), ViT-L, ViT-H (most accurate)
ONNX export: Deploy in browsers and edge devices

Use alternatives instead:

YOLO/Detectron2: For real-time object detection with classes
Mask2Former: For semantic/panoptic segmentation with categories
GroundingDINO + SAM: For text-prompted segmentation
SAM 2: For video segmentation tasks

Quick start

Ordered, practical steps. Run one and confirm it worked before moving on.

Installation

Shell8 lines

# From GitHub
pip install git+https://github.com/facebookresearch/segment-anything.git

# Optional dependencies
pip install opencv-python pycocotools matplotlib

# Or use HuggingFace transformers
pip install transformers

Download checkpoints

Shell8 lines

# ViT-H (largest, most accurate) - 2.4GB
wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth

# ViT-L (medium) - 1.2GB
wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth

# ViT-B (smallest, fastest) - 375MB
wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth

Basic usage with SamPredictor

Python27 lines


from segment_anything import sam_model_registry, SamPredictor

# Load model
sam = sam_model_registry["vit_h"](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything-model/checkpoint="sam_vit_h_4b8939.pth")
sam.to(device="cuda")

# Create predictor
predictor = SamPredictor(sam)

# Set image (computes embeddings once)
image = cv2.imread("image.jpg")
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
predictor.set_image(image)

# Predict with point prompts
input_point = np.array([[500, 375]])  # (x, y) coordinates
input_label = np.array([1])  # 1 = foreground, 0 = background

masks, scores, logits = predictor.predict(
    point_coords=input_point,
    point_labels=input_label,
    multimask_output=True  # Returns 3 mask options
)

# Select best mask
best_mask = masks[np.argmax(scores)]

HuggingFace Transformers

Python26 lines


from PIL import Image
from transformers import SamModel, SamProcessor

# Load model and processor
model = SamModel.from_pretrained("facebook/sam-vit-huge")
processor = SamProcessor.from_pretrained("facebook/sam-vit-huge")
model.to("cuda")

# Process image with point prompt
image = Image.open("image.jpg")
input_points = [[[450, 600]]]  # Batch of points

inputs = processor(image, input_points=input_points, return_tensors="pt")
inputs = {k: v.to("cuda") for k, v in inputs.items()}

# Generate masks
with torch.no_grad():
    outputs = model(**inputs)

# Post-process masks to original size
masks = processor.image_processor.post_process_masks(
    outputs.pred_masks.cpu(),
    inputs["original_sizes"].cpu(),
    inputs["reshaped_input_sizes"].cpu()
)

Core concepts

Explains the idea itself. Read it slowly; the later sections build on it.

Model architecture

Text8 lines

SAM Architecture:
┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐
│  Image Encoder  │────▶│ Prompt Encoder  │────▶│  Mask Decoder   │
│     (ViT)       │     │ (Points/Boxes)  │     │ (Transformer)   │
└─────────────────┘     └─────────────────┘     └─────────────────┘
        │                       │                       │
   Image Embeddings      Prompt Embeddings         Masks + IoU
   (computed once)       (per prompt)             predictions

Model variants

Model	Checkpoint	Size	Speed	Accuracy
ViT-H	`vit_h`	2.4 GB	Slowest	Best
ViT-L	`vit_l`	1.2 GB	Medium	Good
ViT-B	`vit_b`	375 MB	Fastest	Good

Prompt types

Prompt	Description	Use Case
Point (foreground)	Click on object	Single object selection
Point (background)	Click outside object	Exclude regions
Bounding box	Rectangle around object	Larger objects
Previous mask	Low-res mask input	Iterative refinement

Interactive segmentation

Explains the idea itself. Read it slowly; the later sections build on it.

Point prompts

Python19 lines

# Single foreground point
input_point = np.array([[500, 375]])
input_label = np.array([1])

masks, scores, logits = predictor.predict(
    point_coords=input_point,
    point_labels=input_label,
    multimask_output=True
)

# Multiple points (foreground + background)
input_points = np.array([[500, 375], [600, 400], [450, 300]])
input_labels = np.array([1, 1, 0])  # 2 foreground, 1 background

masks, scores, logits = predictor.predict(
    point_coords=input_points,
    point_labels=input_labels,
    multimask_output=False  # Single mask when prompts are clear
)

Box prompts

Python7 lines

# Bounding box [x1, y1, x2, y2]
input_box = np.array([425, 600, 700, 875])

masks, scores, logits = predictor.predict(
    box=input_box,
    multimask_output=False
)

Combined prompts

Python7 lines

# Box + points for precise control
masks, scores, logits = predictor.predict(
    point_coords=np.array([[500, 375]]),
    point_labels=np.array([1]),
    box=np.array([400, 300, 700, 600]),
    multimask_output=False
)

Python14 lines

# Initial prediction
masks, scores, logits = predictor.predict(
    point_coords=np.array([[500, 375]]),
    point_labels=np.array([1]),
    multimask_output=True
)

# Refine with additional point using previous mask
masks, scores, logits = predictor.predict(
    point_coords=np.array([[500, 375], [550, 400]]),
    point_labels=np.array([1, 0]),  # Add background point
    mask_input=logits[np.argmax(scores)][None, :, :],  # Use best mask
    multimask_output=False
)

Automatic mask generation

Explains the idea itself. Read it slowly; the later sections build on it.

Basic automatic segmentation

Python15 lines

from segment_anything import SamAutomaticMaskGenerator

# Create generator
mask_generator = SamAutomaticMaskGenerator(sam)

# Generate all masks
masks = mask_generator.generate(image)

# Each mask contains:
# - segmentation: binary mask
# - bbox: [x, y, w, h]
# - area: pixel count
# - predicted_iou: quality score
# - stability_score: robustness score
# - point_coords: generating point

Customized generation

Python11 lines

mask_generator = SamAutomaticMaskGenerator(
    model=sam,
    points_per_side=32,          # Grid density (more = more masks)
    pred_iou_thresh=0.88,        # Quality threshold
    stability_score_thresh=0.95,  # Stability threshold
    crop_n_layers=1,             # Multi-scale crops
    crop_n_points_downscale_factor=2,
    min_mask_region_area=100,    # Remove tiny masks
)

masks = mask_generator.generate(image)

Filtering masks

Python8 lines

# Sort by area (largest first)
masks = sorted(masks, key=lambda x: x['area'], reverse=True)

# Filter by predicted IoU
high_quality = [m for m in masks if m['predicted_iou'] > 0.9]

# Filter by stability score
stable_masks = [m for m in masks if m['stability_score'] > 0.95]

Batched inference

Explains the idea itself. Read it slowly; the later sections build on it.

Multiple images

Python12 lines

# Process multiple images efficiently
images = [cv2.imread(f"image_{i}.jpg") for i in range(10)]

all_masks = []
for image in images:
    predictor.set_image(image)
    masks, _, _ = predictor.predict(
        point_coords=np.array([[500, 375]]),
        point_labels=np.array([1]),
        multimask_output=True
    )
    all_masks.append(masks)

Multiple prompts per image

Python18 lines

# Process multiple prompts efficiently (one image encoding)
predictor.set_image(image)

# Batch of point prompts
points = [
    np.array([[100, 100]]),
    np.array([[200, 200]]),
    np.array([[300, 300]])
]

all_masks = []
for point in points:
    masks, scores, _ = predictor.predict(
        point_coords=point,
        point_labels=np.array([1]),
        multimask_output=True
    )
    all_masks.append(masks[np.argmax(scores)])

ONNX deployment

Explains the idea itself. Read it slowly; the later sections build on it.

Export model

Shell5 lines

python scripts/export_onnx_model.py \
    --checkpoint sam_vit_h_4b8939.pth \
    --model-type vit_h \
    --output sam_onnx.onnx \
    --return-single-mask

Use ONNX model

Python17 lines



# Load ONNX model
ort_session = onnxruntime.InferenceSession("sam_onnx.onnx")

# Run inference (image embeddings computed separately)
masks = ort_session.run(
    None,
    {
        "image_embeddings": image_embeddings,
        "point_coords": point_coords,
        "point_labels": point_labels,
        "mask_input": np.zeros((1, 1, 256, 256), dtype=np.float32),
        "has_mask_input": np.array([0], dtype=np.float32),
        "orig_im_size": np.array([h, w], dtype=np.float32)
    }
)

Common workflows

Settings you configure once. Change one at a time so you can see what each does. Set EVENT_LBUTTONDOWN, IMREAD_GRAYSCALE in your environment, not in the chat.

Workflow 1: Annotation tool

Python16 lines



# Load model
predictor = SamPredictor(sam)
predictor.set_image(image)

def on_click(event, x, y, flags, param):
    if event == cv2.EVENT_LBUTTONDOWN:
        # Foreground point
        masks, scores, _ = predictor.predict(
            point_coords=np.array([[x, y]]),
            point_labels=np.array([1]),
            multimask_output=True
        )
        # Display best mask
        display_mask(masks[np.argmax(scores)])

Workflow 2: Object extraction

Python18 lines

def extract_object(image, point):
    """Extract object at point with transparent background."""
    predictor.set_image(image)

    masks, scores, _ = predictor.predict(
        point_coords=np.array([point]),
        point_labels=np.array([1]),
        multimask_output=True
    )

    best_mask = masks[np.argmax(scores)]

    # Create RGBA output
    rgba = np.zeros((image.shape[0], image.shape[1], 4), dtype=np.uint8)
    rgba[:, :, :3] = image
    rgba[:, :, 3] = best_mask * 255

    return rgba

Workflow 3: Medical image segmentation

Python11 lines

# Process medical images (grayscale to RGB)
medical_image = cv2.imread("scan.png", cv2.IMREAD_GRAYSCALE)
rgb_image = cv2.cvtColor(medical_image, cv2.COLOR_GRAY2RGB)

predictor.set_image(rgb_image)

# Segment region of interest
masks, scores, _ = predictor.predict(
    box=np.array([x1, y1, x2, y2]),  # ROI bounding box
    multimask_output=True
)

Output format

Explains the idea itself. Read it slowly; the later sections build on it.

Mask data structure

Python10 lines

# SamAutomaticMaskGenerator output
{
    "segmentation": np.ndarray,  # H×W binary mask
    "bbox": [x, y, w, h],        # Bounding box
    "area": int,                 # Pixel count
    "predicted_iou": float,      # 0-1 quality score
    "stability_score": float,    # 0-1 robustness score
    "crop_box": [x, y, w, h],    # Generation crop region
    "point_coords": [[x, y]],    # Input point
}

COCO RLE format

Python8 lines

from pycocotools import mask as mask_utils

# Encode mask to RLE
rle = mask_utils.encode(np.asfortranarray(mask.astype(np.uint8)))
rle["counts"] = rle["counts"].decode("utf-8")

# Decode RLE to mask
decoded_mask = mask_utils.decode(rle)

Performance optimization

Explains the idea itself. Read it slowly; the later sections build on it.

GPU memory

Python6 lines

# Use smaller model for limited VRAM
sam = sam_model_registry["vit_b"](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything-model/checkpoint="sam_vit_b_01ec64.pth")

# Process images in batches
# Clear CUDA cache between large batches
torch.cuda.empty_cache()

Speed optimization

Python11 lines

# Use half precision
sam = sam.half()

# Reduce points for automatic generation
mask_generator = SamAutomaticMaskGenerator(
    model=sam,
    points_per_side=16,  # Default is 32
)

# Use ONNX for deployment
# Export with --return-single-mask for faster inference

Common issues

A lookup table. Do not read it all; find the row that applies to you.

Issue	Solution
Out of memory	Use ViT-B model, reduce image size
Slow inference	Use ViT-B, reduce points_per_side
Poor mask quality	Try different prompts, use box + points
Edge artifacts	Use stability_score filtering
Small objects missed	Increase points_per_side

References

Explains the idea itself. Read it slowly; the later sections build on it.

Advanced Usage ↗ - Batching, fine-tuning, integration
Troubleshooting ↗ - Common issues and solutions

Resources

Explains the idea itself. Read it slowly; the later sections build on it.

GitHub: https://github.com/facebookresearch/segment-anything
Paper: https://arxiv.org/abs/2304.02643
Demo: https://segment-anything.com
SAM 2 (Video): https://github.com/facebookresearch/segment-anything-2
HuggingFace: https://huggingface.co/facebook/sam-vit-huge

Segment Anything Model

What does it add to Hermes?

Inspect, install, then test.

Review the command, then copy it.

Exactly what Hermes loads when this skill runs.

Installation

Download checkpoints

Basic usage with SamPredictor

HuggingFace Transformers

Model architecture

Model variants

Prompt types

Point prompts

Box prompts

Combined prompts

Iterative refinement

Basic automatic segmentation

Customized generation

Filtering masks

Multiple images

Multiple prompts per image

Export model

Use ONNX model

Workflow 1: Annotation tool

Workflow 2: Object extraction

Workflow 3: Medical image segmentation

Mask data structure

COCO RLE format

GPU memory

Speed optimization