Projects » Forks of other projects » TrafficStreamYOLO

TrafficStreamYOLO

Detecting Lex traffic using YOLOv7

Archived This repository is archived: read-only and no longer maintained.

Fork A fork of WongKinYiu/yolov7; the README may describe the upstream project.

Overview

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Docker environment (recommended) Expand

yolov7.pt yolov7x.pt yolov7-w6.pt yolov7-e6.pt yolov7-d6.pt yolov7-e6e.pt

To measure accuracy, download COCO-annotations for Pycocotools to the ./coco/annotations/instances_val2017.json

yolov7_training.pt yolov7x_training.pt yolov7-w6_training.pt yolov7-e6_training.pt yolov7-d6_training.pt yolov7-e6e_training.pt

Single GPU finetuning for custom dataset

Pytorch to CoreML (and inference on MacOS/iOS)

Pytorch to ONNX with NMS (and inference)

Pytorch to TensorRT with NMS (and inference)

Pytorch to TensorRT another way Expand

Tested with: Python 3.7.13, Pytorch 1.12.0+cu113

YOLOv7 for instance segmentation (YOLOR + YOLOv5 + YOLACT)

YOLOv7 with decoupled TAL head (YOLOR + YOLOv5 + YOLOv6)

Yolov7-semantic & YOLOv7-panoptic & YOLOv7-caption

From the project’s README on GitHub.

At a glance

RepositoryKentucky-Open-Science/TrafficStreamYOLO
Research areaForks of other projects
Primary languageJupyter Notebook
LanguagesJupyter Notebook 98.8%, Python 1.2%
LicenseGPL-3.0
Stars / forks0 / 0
Open issues and pull requests4
Created2023-01-09
Last push2026-02-10
Default branchmain
Forked fromWongKinYiu/yolov7 — Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

What the README covers

Top contributors

Get the code

git clone https://github.com/Kentucky-Open-Science/TrafficStreamYOLO.git