metadata
license: apache-2.0
tags:
- object-detection
- person-detection
- rtmdet
- real-time
- computer-vision
pipeline_tag: object-detection
rtmdet-tiny
This is a Hugging Face-compatible port of rtmdet-tiny from OpenMMLab MMDetection.
RTMDet is a family of real-time object detectors based on the CSPNeXt architecture. This checkpoint is pretrained on COCO and is particularly well-suited for person detection as a first stage before wholebody pose estimation with RTMW.
Model description
- Architecture: CSPNeXt backbone + CSPNeXtPAFPN neck + RTMDetHead
- Backbone scale: deepen=0.167, widen=0.375 (~~5M parameters)
- Input size: 640×640
- Classes: 80 (COCO)
- Uses custom code — load with
trust_remote_code=True
Usage
from transformers import AutoConfig, AutoModel, AutoImageProcessor
from PIL import Image
import torch
config = AutoConfig.from_pretrained("akore/rtmdet-tiny", trust_remote_code=True)
model = AutoModel.from_pretrained("akore/rtmdet-tiny", trust_remote_code=True)
model.eval()
processor = AutoImageProcessor.from_pretrained("akore/rtmdet-tiny")
image = Image.open("your_image.jpg").convert("RGB")
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(pixel_values=inputs["pixel_values"])
# outputs["boxes"]: (N, 4) in [x1, y1, x2, y2]
# outputs["scores"]: (N,)
# outputs["labels"]: (N,) — 0 = person in COCO
print(outputs)
Citation
@misc{lyu2022rtmdet,
title={RTMDet: An Empirical Study of Designing Real-Time Object Detectors},
author={Chengqi Lyu and Wenwei Zhang and Haian Huang and Yue Zhou and Yudong Wang and Yanyi Liu and Shilong Zhang and Kai Chen},
year={2022},
eprint={2212.07784},
archivePrefix={arXiv},
primaryClass={cs.CV}
}