yolos-small-person / README.md
AdamCodd's picture
Update README.md
936c3a2 verified
|
raw
history blame
4.71 kB
metadata
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 by Fang et al. and first released in this repository. model_image

Model description

This hustvl/yolos-small model has been finetuned on these two datasets[1][2] (2604 samples) with the following results on the test set:

 IoU metric: bbox
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.472
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.856
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.494
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.029
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.420
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.633
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.381
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.587
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.662
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.157
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.647
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.775

How to use

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 for more code examples.

Intended uses & limitations

This model is more of an experiment on a small scale and will need retraining on a more diverse dataset. This fine-tuned model performs best when detecting individuals who are relatively 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: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08
  • num_epochs: 5
  • weight_decay: 1e-4

Framework versions

  • Transformers 4.37.0
  • pycocotools 2.0.7

If you want to support me, you can here.

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}
}