transformers/docs/source/en/model_doc/sam.md

This model was published in HF papers on 2023-04-05 and contributed to Hugging Face Transformers on 2023-04-19.

SAM

Overview

SAM (Segment Anything Model) was proposed in Segment Anything by Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alex Berg, Wan-Yen Lo, Piotr Dollar, Ross Girshick.

The model can be used to predict segmentation masks of any object of interest given an input image.

The abstract from the paper is the following:

We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensed and privacy respecting images. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks. We evaluate its capabilities on numerous tasks and find that its zero-shot performance is impressive -- often competitive with or even superior to prior fully supervised results. We are releasing the Segment Anything Model (SAM) and corresponding dataset (SA-1B) of 1B masks and 11M images at https://segment-anything.com to foster research into foundation models for computer vision.

Tips:

• The model predicts binary masks that states the presence or not of the object of interest given an image.
• The model predicts much better results if input 2D points and/or input bounding boxes are provided
• You can prompt multiple points for the same image, and predict a single mask.
• Fine-tuning the model is not supported yet
• According to the paper, textual input should be also supported. However, at this time of writing this seems not to be supported according to the official repository.

This model was contributed by ybelkada and ArthurZ. The original code can be found here.

Below is an example on how to run mask generation given an image and a 2D point:

import requests
import torch
from PIL import Image

from transformers import SamModel, SamProcessor


model = SamModel.from_pretrained("facebook/sam-vit-huge", device_map="auto")
processor = SamProcessor.from_pretrained("facebook/sam-vit-huge")

img_url = "https://huggingface.co/ybelkada/segment-anything/resolve/main/assets/car.png"
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert("RGB")
input_points = [[[450, 600]]]  # 2D location of a window in the image

inputs = processor(raw_image, input_points=input_points, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model(**inputs)

masks = processor.image_processor.post_process_masks(
    outputs.pred_masks.cpu(), inputs["original_sizes"].cpu(), inputs["reshaped_input_sizes"].cpu()
)
scores = outputs.iou_scores

You can also process your own masks alongside the input images in the processor to be passed to the model.

import requests
import torch
from PIL import Image

from transformers import SamModel, SamProcessor


model = SamModel.from_pretrained("facebook/sam-vit-huge", device_map="auto")
processor = SamProcessor.from_pretrained("facebook/sam-vit-huge")

img_url = "https://huggingface.co/ybelkada/segment-anything/resolve/main/assets/car.png"
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert("RGB")
mask_url = "https://huggingface.co/ybelkada/segment-anything/resolve/main/assets/car.png"
segmentation_map = Image.open(requests.get(mask_url, stream=True).raw).convert("1")
input_points = [[[450, 600]]]  # 2D location of a window in the image

inputs = processor(raw_image, input_points=input_points, segmentation_maps=segmentation_map, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model(**inputs)

masks = processor.image_processor.post_process_masks(
    outputs.pred_masks.cpu(), inputs["original_sizes"].cpu(), inputs["reshaped_input_sizes"].cpu()
)
scores = outputs.iou_scores

Resources

A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with SAM.

• Demo notebook for using the model.
• Demo notebook for using the automatic mask generation pipeline.
• Demo notebook for inference with MedSAM, a fine-tuned version of SAM on the medical domain. 🌎
• Demo notebook for fine-tuning the model on custom data. 🌎

SlimSAM

SlimSAM, a pruned version of SAM, was proposed in 0.1% Data Makes Segment Anything Slim by Zigeng Chen et al. SlimSAM reduces the size of the SAM models considerably while maintaining the same performance.

Checkpoints can be found on the hub, and they can be used as a drop-in replacement of SAM.

Grounded SAM

One can combine Grounding DINO with SAM for text-based mask generation as introduced in Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks. You can refer to this demo notebook 🌍 for details.

Grounded SAM overview. Taken from the original repository.

SamConfig

autodoc SamConfig

SamVisionConfig

autodoc SamVisionConfig

SamMaskDecoderConfig

autodoc SamMaskDecoderConfig

SamPromptEncoderConfig

autodoc SamPromptEncoderConfig

SamProcessor

autodoc SamProcessor - call

SamImageProcessor

autodoc SamImageProcessor - preprocess

SamImageProcessorPil

autodoc SamImageProcessorPil - preprocess

SamVisionModel

autodoc SamVisionModel - forward

SamModel

autodoc SamModel - forward