Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/qq44642754a/Yolov5_ros
Real-time object detection with ROS, based on YOLOv5 and PyTorch (基于 YOLOv5的ROS实时对象检测)
https://github.com/qq44642754a/Yolov5_ros
pytorch ros yolov5
Last synced: 12 days ago
JSON representation
Real-time object detection with ROS, based on YOLOv5 and PyTorch (基于 YOLOv5的ROS实时对象检测)
- Host: GitHub
- URL: https://github.com/qq44642754a/Yolov5_ros
- Owner: qq44642754a
- Created: 2022-01-17T04:45:28.000Z (over 2 years ago)
- Default Branch: master
- Last Pushed: 2024-02-06T13:41:27.000Z (5 months ago)
- Last Synced: 2024-02-29T05:38:04.864Z (4 months ago)
- Topics: pytorch, ros, yolov5
- Language: Python
- Homepage:
- Size: 107 MB
- Stars: 100
- Watchers: 1
- Forks: 18
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
Lists
- awesome-yolo-object-detection - qq44642754a/Yolov5_ros - time object detection with ROS, based on YOLOv5 and PyTorch (基于 YOLOv5的ROS实时对象检测). (Other Versions of YOLO)
README
# Yolov5_ros
For simplified Chinese version: [简体中文版](./README_CN.md)
This package provides a ROS wrapper for [PyTorch-YOLOv5](https://github.com/ultralytics/yolov5) based on PyTorch-YOLOv5. The package has been tested with Ubuntu 16.04 and Ubuntu 18.04.
V1.0.1: Add device options(cpu or gpu).
**Authors**: Zhitao Zheng ()
# develop environment：
- Ubuntu 16.04 / 18.04
- ROS Kinetic / Melodic
- Python>=3.6.0 environment, including PyTorch>=1.7
# Prerequisites:
## Install Anaconda:
### 1. First download the corresponding installation package [Anaconda](https://www.anaconda.com/products/individual#linux)
### 2. Then install anaconda （for example）
```
bash ~/Downloads/Anaconda3-2021.05-Linux-x86_64.sh
```
### 3. Edit the ~/.bashrc file and add it at the end
```
export PATH=/home/your/anaconda3/bin:$PATH
```
### 4. Execute after save and exit:
```
source ~/.bashrc
```
## Install Pytorch:
### 1. First create an anaconda virtual environment for pytorch
```
conda create -n mypytorch python=3.8
```
### 2. activate the mypytorch environment
```
conda activate mypytorch
```
### 3. Install pytorch1.8 in the created pytorch environment
Install PyTorch: https://pytorch.org/get-started/locally/
```
conda install pytorch torchvision cudatoolkit=10.2 -c pytorch
```
### 4. Edit ~/.bashrc file, set to use python3.8 in mypytorch environment
```
alias python='/home/your/anaconda3/envs/mypytorch/bin/python3.8'
```
### 5. Execute after save and exit:
```
source ~/.bashrc
```
## Installation yolov5_ros
```
cd /your/catkin_ws/src
git clone https://github.com/qq44642754a/Yolov5_ros.git
cd yolov5_ros/yolov5
sudo pip install -r requirements.txt
```
## Basic Usage
1. First, make sure to put your weights in the [weights](https://github.com/qq44642754a/Yolov5_ros/tree/master/yolov5_ros/yolov5_ros/weights) folder.
2. The default settings (using `yolov5s.pt`) in the `launch/yolo_v5.launch` file should work, all you should have to do is change the image topic you would like to subscribe to:
```
roslaunch yolov5_ros yolo_v5.launch
```
Alternatively you can modify the parameters in the [launch file](https://github.com/qq44642754a/Yolov5_ros/tree/master/yolov5_ros/launch/yolo_v5.launch), recompile and launch it that way so that no arguments need to be passed at runtime.
### Node parameters
* **`image_topic`**
Subscribed camera topic.
* **`weights_path`**
Path to weights file.
* **`pub_topic`**
Published topic with the detected bounding boxes.
* **`confidence`**
Confidence threshold for detected objects.