---
license: apache-2.0
base_model: hustvl/yolos-small
tags:
- object-detection
- vision
widget:
- src: https://i.imgur.com/MjMfEMk.jpeg
  example_title: Children
---

# Yolos-small-person

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](https://arxiv.org/abs/2106.00666) by Fang et al. and first released in [this repository](https://github.com/hustvl/YOLOS). 
![model_image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/yolos_architecture.png)


## Model description
This model has been finetuned on the following [crowd-detection dataset](https://universe.roboflow.com/institut-teknologi-nasional-bandung-mxgtc/crowd-detection-i75bl) (669 samples) with the following results on the test set:

```
IoU metric: bbox
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.630
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.908
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.672
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.005
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.636
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.431
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.740
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.762
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.300
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.766
```

## How to use

```python
from transformers import AutoImageProcessor, AutoModelForObjectDetection
import torch
from PIL import Image
import requests

url = "https://latestbollyholly.com/wp-content/uploads/2024/02/Jacob-Gooch.jpg"
image = Image.open(requests.get(url, stream=True).raw)
image_processor = AutoImageProcessor.from_pretrained("AdamCodd/yolos-small-person")
model = AutoModelForObjectDetection.from_pretrained("AdamCodd/yolos-small-person")
inputs = image_processor(images=image, return_tensors="pt")
outputs = model(**inputs)

# convert outputs (bounding boxes and class logits) to Pascal VOC format (xmin, ymin, xmax, ymax)
target_sizes = torch.tensor([image.size[::-1]])
results = image_processor.post_process_object_detection(outputs, threshold=0.7, target_sizes=target_sizes)[0]
for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
    box = [round(i, 2) for i in box.tolist()]
    print(
        f"Detected {model.config.id2label[label.item()]} with confidence "
        f"{round(score.item(), 3)} at location {box}"
    )
```

Refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/yolos) for more code examples.

## Intended uses & limitations

This model is more of an experiment on a small scale and will need retraining on a better dataset. This fine-tuned model performs best when detecting individuals who are relatively close (but not too close) to the viewpoint. As indicated by the metrics, it struggles to identify individuals farther away.

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08
- num_epochs: 5
- weight_decay: 1e-4

### Framework versions

- Transformers 4.36.2
- pycocotools 2.0.7

If you want to support me, you can [here](https://ko-fi.com/adamcodd).

### 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}
}
```