README.md

---
pipeline_tag: mask-generation
license: apache-2.0
base_model: facebook/sam-vit-base
library_name: zeromodels
tags:
- keras
- zeromodels
- sam
- mask-generation
- image-segmentation
- arxiv:2304.02643
- pytorch
- jax
- tf
---

## ***See [our collection](https://huggingface.co/collections/zeromodels/sam-v1-v2-v3-6a8eaf73a274fffa2ea83cfd) for all versions of SAM.***

# Run SAM with Keras 3: JAX, PyTorch, or TensorFlow

[![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-black?logo=github)](https://github.com/IMvision12/ZeroModels) [![Docs](https://img.shields.io/badge/Docs-SAM-blue)](https://imvision12.github.io/ZeroModels/sam/) [![Collection](https://img.shields.io/badge/HF-SAM%20collection-yellow)](https://huggingface.co/collections/zeromodels/sam-v1-v2-v3-6a8eaf73a274fffa2ea83cfd)

# zeromodels/sam_vit_base

Paper: [Segment Anything (arXiv:2304.02643)](https://arxiv.org/abs/2304.02643) · [HF Papers](https://huggingface.co/papers/2304.02643)

SAM (Segment Anything Model) segments whatever you point at. It has no class vocabulary: you give it a prompt (a click or a box) and it returns a mask. A heavy ViT image encoder runs once per image; the prompt encoder and mask decoder are light enough for interactive use.

For more details on the model, please go to Meta's original [model card](https://huggingface.co/facebook/sam-vit-base).

Pure-**Keras 3** conversion of [`facebook/sam-vit-base`](https://huggingface.co/facebook/sam-vit-base) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**.

This is a **promptable segmentation** checkpoint (`SAMPromptableSegment`): point (and optional box) prompts, backbone ViT-B.

## ✨ Quick start

```python
import os
os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"

import numpy as np
from PIL import Image
from zeromodels.models.sam import (
    SAMPromptableSegment,
    SAMProcessor,
)

model = SAMPromptableSegment.from_weights("zeromodels/sam_vit_base")
processor = SAMProcessor.from_weights("zeromodels/sam_vit_base")

image = Image.open("your_image.jpg").convert("RGB")
inputs = processor(
    image,
    input_points=np.array([[[[450, 200]]]], dtype="float32"),
    input_labels=np.array([[[1]]], dtype="int32"),
)
META = ("original_size", "reshaped_size")
output = model({k: v for k, v in inputs.items() if k not in META})
masks = processor.post_process_masks(
    output["pred_masks"], original_size=inputs["original_size"]
)
print(output["iou_scores"].shape, masks.shape)
```

Load any SAM / SAM2 / SAM3 variant the same way with `from_weights("zeromodels/<variant>")` (use `SAMPromptableSegment` for this repo):

| Variant | Hub | Family |
|---|---|---|
| `sam_vit_base` | [`zeromodels/sam_vit_base`](https://huggingface.co/zeromodels/sam_vit_base) | SAM |
| `sam_vit_large` | [`zeromodels/sam_vit_large`](https://huggingface.co/zeromodels/sam_vit_large) | SAM |
| `sam_vit_huge` | [`zeromodels/sam_vit_huge`](https://huggingface.co/zeromodels/sam_vit_huge) | SAM |
| `sam2_hiera_small` | [`zeromodels/sam2_hiera_small`](https://huggingface.co/zeromodels/sam2_hiera_small) | SAM2 |
| `sam2_hiera_base_plus` | [`zeromodels/sam2_hiera_base_plus`](https://huggingface.co/zeromodels/sam2_hiera_base_plus) | SAM2 |
| `sam2_hiera_large` | [`zeromodels/sam2_hiera_large`](https://huggingface.co/zeromodels/sam2_hiera_large) | SAM2 |
| `sam3` | [`zeromodels/sam3`](https://huggingface.co/zeromodels/sam3) | SAM3 |

## Tips

- Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
- SAM / SAM2: point coordinates are in original pixel space; box prompts need `enable_boxes=True` / `include_box_input=True` when building the graph.
- SAM2 in this port is image-only (no video memory bank).
- SAM3: prefer `SAM3InstanceSegment.predict(...)` for text prompts; upstream `facebook/sam3` is gated.
- See [SAM docs](https://imvision12.github.io/ZeroModels/sam/) and [Loading Weights](https://imvision12.github.io/ZeroModels/loading_weights/).
- Community / upstream safetensors still work via the `hf:` prefix, e.g. `SAMPromptableSegment.from_weights("hf:facebook/sam-vit-base")`.

## Special Thanks

A huge thank you to the Meta Segment Anything authors for creating and releasing these models.

License: Apache 2.0.