YOLOS (tiny-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:

from transformers import YolosImageProcessor, YolosForObjectDetection
from PIL import Image
import torch
import requests

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

model = YolosForObjectDetection.from_pretrained('hustvl/yolos-tiny')
image_processor = YolosImageProcessor.from_pretrained("hustvl/yolos-tiny")

inputs = image_processor(images=image, return_tensors="pt")
outputs = model(**inputs)

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


# print results
target_sizes = torch.tensor([image.size[::-1]])
results = image_processor.post_process_object_detection(outputs, threshold=0.9, 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}"
    )

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 300 epochs on ImageNet-1k and fine-tuned for 300 epochs on COCO.

Evaluation results

This model achieves an AP (average precision) of 28.7 on COCO 2017 validation. For more details regarding evaluation results, we refer to the original paper.

BibTeX entry and citation info

@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}
}