Skip to content

Latest commit

 

History

History
100 lines (77 loc) · 3.85 KB

datvuthanh_hybridnets.md

File metadata and controls

100 lines (77 loc) · 3.85 KB
Raw
layout background-class body-class category title summary image author tags github-link github-id featured_image_1 featured_image_2 accelerator demo-model-link
hub_detail
hub-background
hub
researchers
HybridNets
HybridNets - End2End Perception Network
hybridnets.jpg
Dat Vu Thanh
vision
datvuthanh/HybridNets
no-image
no-image
cuda-optional

Before You Start

Start from a Python>=3.7 environment with PyTorch>=1.10 installed. To install PyTorch see https://pytorch.org/get-started/locally/. To install HybridNets dependencies:

pip install -qr https://raw.githubusercontent.com/datvuthanh/HybridNets/main/requirements.txt  # install dependencies

Model Description

HybridNets is an end2end perception network for multi-tasks. Our work focused on traffic object detection, drivable area segmentation and lane detection. HybridNets can run real-time on embedded systems, and obtains SOTA Object Detection, Lane Detection on BDD100K Dataset.

Results

Traffic Object Detection

Model Recall (%) [email protected] (%)
MultiNet 81.3 60.2
DLT-Net 89.4 68.4
Faster R-CNN 77.2 55.6
YOLOv5s 86.8 77.2
YOLOP 89.2 76.5
HybridNets 92.8 77.3

Drivable Area Segmentation

Model Drivable mIoU (%)
MultiNet 71.6
DLT-Net 71.3
PSPNet 89.6
YOLOP 91.5
HybridNets 90.5

Lane Line Detection

Model Accuracy (%) Lane Line IoU (%)
Enet 34.12 14.64
SCNN 35.79 15.84
Enet-SAD 36.56 16.02
YOLOP 70.5 26.2
HybridNets 85.4 31.6

Load From PyTorch Hub

This example loads the pretrained HybridNets model and passes an image for inference.

import torch

# load model
model = torch.hub.load('datvuthanh/hybridnets', 'hybridnets', pretrained=True)

#inference
img = torch.randn(1,3,640,384)
features, regression, classification, anchors, segmentation = model(img)

Citation

If you find our paper and code useful for your research, please consider giving a star and citation:

@misc{vu2022hybridnets,
      title={HybridNets: End-to-End Perception Network}, 
      author={Dat Vu and Bao Ngo and Hung Phan},
      year={2022},
      eprint={2203.09035},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}