sam-license
Modellquelle
Quellenbeschreibung
This is an ungated mirror of Meta's SAM3 model weights, redistributed under the SAM License for easier access.
SAM3 (Segment Anything Model 3) is Meta AI's state-of-the-art foundation model for in images and videos. It supports:
Quellen
1 QuelleVerifiziert 27. Sept.
Modellartefakte
1 ArtefaktQuellenauszüge
2 Auszüge| File | Description |
|---|---|
sam3.safetensors | Model weights (safetensors format, converted from official .pt) |
LICENSE | SAM License (required for redistribution) |
The sam3.safetensors in this repo is converted directly from the official sam3.pt checkpoint using:
import torch
from safetensors.torch import save_file
state_dict = torch.load("sam3.pt", map_location="cpu")
save_file(state_dict, "sam3.safetensors")
This preserves the original key names (detector.*, tracker.*). Do not use the HuggingFace Transformers-format safetensors from facebook/sam3 — those have different key names (detector_model.*) and are incompatible with build_sam3_video_model().
# With the official sam3 package
pip install sam3
from sam3.model_builder import build_sam3_image_model
model = build_sam3_image_model(checkpoint_path="sam3.safetensors")
This model is distributed under the SAM License — see the LICENSE file. Key points:
--- license: other license_name: sam-license license_link: LICENSE tags: - segmentation - image-segmentation - video-segmentation - sam3 - meta - pytorch - safetensors pipeline_tag: image-segmentation base_model: facebook/sam3 --- # SAM3 — Segment Anything Model 3 This is an **ungated mirror** of Meta's [SAM3](https://github.com/facebookresearch/sam3) model weights, redistributed under the [SAM License](LICENSE) for easier access. ## What is SAM3? SAM3 (Segment Anything Model 3) is Meta AI's state-of-the-art foundation model for **promptable segmentation** in images and videos. It supports: - **Text prompts** — segment objects by describing them (e.g. *"the dog"*) - **Bounding box prompts** — precise region targeting - **Point prompts** — click-to-segment - **Video tracking** — track and segment objects across video frames - **Automatic mask generation** — segment all objects in a scene ## Files | File | Description | |---|---| | `sam3.safetensors` | Model weights (safetensors format, converted from official `.pt`) | | `LICENSE` | SAM License (required for redistribution) | ## ⚠️ Conversion Note The `sam3.safetensors` in this repo is converted **directly from the official `sam3.pt`** checkpoint using: ```python import torch from safetensors.torch import save_file state_dict = torch.load("sam3.pt", map_location="cpu") save_file(state_dict, "sam3.safetensors") ``` This preserves the original key names (`detector.*`, `tracker.*`). Do **not** use the HuggingFace Transformers-format safetensors from `facebook/sam3` — those have different key names (`detector_model.*`) and are **incompatible** with `build_sam3_video_model()`. ## Usage ```python # With the official sam3 package pip install sam3 from sam3.model_builder import build_sam3_image_model model = build_sam3_image_model(checkpoint_path="sam3.safetensors") ``` ## License This model is distributed under the **SAM License** — see the [LICENSE](LICENSE) file. Key points: - ✅ Commercial use permitted - ✅ Redistribution permitted (with license included) - ✅ Derivative works permitted - ❌ No military/warfare, nuclear, or espionage use - ❌ No reverse engineering ## Credits - **Original model by**: [Meta AI (FAIR)](https://github.com/facebookresearch/sam3) - **Original HuggingFace repo**: [facebook/sam3](https://huggingface.co/facebook/sam3) - **Paper**: *Segment Anything Model 3* (subm...
Source context: 329 downloads · 7 likes · Pipeline image-segmentation · Repo AEmotionStudio/sam3