neeze/tools_detection

Tools Detection

Description

Tools_Detection
├── config
├── data
│   ├── test
│   │   ├── images
│   │   └── labels
│   ├── train
│   │   ├── images
│   │   └── labels
│   └── val
│       ├── images
│       └── labels
├── scripts
└── src
    ├── models
    └── utils

Prerequisites

Before you begin, ensure you have met the following requirements:

• You have installed the version of python==3.10.13
• Modules: numpy, torch, torchvision, tqdm, torchsummary, torchmetrics, torchinfo, sklearn, wandb, pycocotools, opencv-python, matplotlib, seaborn

Quickstart

Clone the repo

git clone https://github.com/Neeze/Tools_Detection.git

Install Dependencies

pip install numpy torch torchvision tqdm torchsummary torchmetrics torchinfo scikit-learn wandb pycocotools opencv-python matplotlib seaborn roboflow --quiet

Download dataset

from roboflow import Roboflow
rf = Roboflow(api_key="WAWzuRQeZQxeCnJr4hHR")
project = rf.workspace("fpt-ycwb3").project("tool_detections")
version = project.version(1)
dataset = version.download("yolov8")

Before training run this

python scripts/yolo2voc.py --config config/faster_rcnn18_config.yaml

Training model

python scripts/train.py --config config/faster_rcnn18_config.yaml