Overview

YOLOS-Small is a streamlined object detection model that replaces traditional convolutional backbones with a Vision Transformer (ViT) architecture. By treating detection as a sequence-to-sequence problem, it eliminates the need for complex hand-crafted components like anchor boxes or non-maximum suppression (NMS) during inference. For developers, this means a more unified pipeline and easier integration into existing PyTorch or TensorFlow workflows. While it maintains a smaller footprint for faster deployment, it remains highly effective for real-time visual recognition tasks. It is particularly useful for edge computing applications or as a baseline for fine-tuning on custom domain-specific datasets where low latency is critical.

Highlights

Transformer-based architecture eliminates complex anchor box configurations
Optimized small footprint for low-latency edge deployment
Apache-2.0 license allows flexible commercial integration
Simplified end-to-end pipeline reduces post-processing overhead

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("hustvl/yolos-small")
tokenizer = AutoTokenizer.from_pretrained("hustvl/yolos-small")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download hustvl/yolos-small

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download hustvl/yolos-small config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('hustvl/yolos-small')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/hustvl/yolos-small

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/hustvl/yolos-small

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('hustvl/yolos-small')
tokenizer = AutoTokenizer.from_pretrained('hustvl/yolos-small')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model hustvl/yolos-small

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model hustvl/yolos-small README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('hustvl/yolos-small')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/hustvl/yolos-small.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/hustvl/yolos-small.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'hustvl/yolos-small')

Full Documentation

来源: HuggingFace

---
license: apache-2.0
tags:

object-detection

vision

datasets:

coco

widget:

src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg

example_title: Savanna

src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg

example_title: Football Match

src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg

example_title: Airport
---

YOLOS (small-sized) model

YOLOS model fine-tuned on COCO 2017 object detection (118k annotated images). It was introduced in the paper You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection by Fang et al. and first released in this repository.

Disclaimer: The team releasing YOLOS did not write a model card for this model so this model card has been written by the Hugging Face team.

Model description

YOLOS is a Vision Transformer (ViT) trained using the DETR loss. Despite its simplicity, a base-sized YOLOS model is able to achieve 42 AP on COCO validation 2017 (similar to DETR and more complex frameworks such as Faster R-CNN).

The model is trained using a "bipartite matching loss": one compares the predicted classes + bounding boxes of each of the N = 100 object queries to the ground truth annotations, padded up to the same length N (so if an image only contains 4 objects, 96 annotations will just have a "no object" as class and "no bounding box" as bounding box). The Hungarian matching algorithm is used to create an optimal one-to-one mapping between each of the N queries and each of the N annotations. Next, standard cross-entropy (for the classes) and a linear combination of the L1 and generalized IoU loss (for the bounding boxes) are used to optimize the parameters of the model.

Intended uses & limitations

You can use the raw model for object detection. See the model hub to look for all available YOLOS models.

How to use

Here is how to use this model:

python

from transformers import YolosFeatureExtractor, YolosForObjectDetection
from PIL import Image
import requests
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
feature_extractor = YolosFeatureExtractor.from_pretrained('hustvl/yolos-small')
model = YolosForObjectDetection.from_pretrained('hustvl/yolos-small')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(inputs)

model predicts bounding boxes and corresponding COCO classes
logits = outputs.logits
bboxes = outputs.pred_boxes

Currently, both the feature extractor and model support PyTorch.

Training data

The YOLOS model was pre-trained on ImageNet-1k and fine-tuned on COCO 2017 object detection, a dataset consisting of 118k/5k annotated images for training/validation respectively.

Training

The model was pre-trained for 200 epochs on ImageNet-1k and fine-tuned for 150 epochs on COCO.

Evaluation results

This model achieves an AP (average precision) of 36.1** on COCO 2017 validation. For more details regarding evaluation results, we refer to table 1 of the original paper.

BibTeX entry and citation info

bibtex

@article{DBLP:journals/corr/abs-2106-00666,
  author    = {Yuxin Fang and
               Bencheng Liao and
               Xinggang Wang and
               Jiemin Fang and
               Jiyang Qi and
               Rui Wu and
               Jianwei Niu and
               Wenyu Liu},
  title     = {You Only Look at One Sequence: Rethinking Transformer in Vision through
               Object Detection},
  journal   = {CoRR},
  volume    = {abs/2106.00666},
  year      = {2021},
  url       = {https://arxiv.org/abs/2106.00666},
  eprinttype = {arXiv},
  eprint    = {2106.00666},
  timestamp = {Fri, 29 Apr 2022 19:49:16 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2106-00666.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

yolos small

Overview

Highlights

Usage

Hugging Face Download

CLI Download

SDK Download

Git Download

PyTorch / Transformers Usage

Model Download

CLI Download

SDK Download

Git Download

Notebook Quickstart

Full Documentation

YOLOS (small-sized) model

Model description

Intended uses & limitations

How to use

model predicts bounding boxes and corresponding COCO classes

Training data

Training

Evaluation results

BibTeX entry and citation info