search

biswadeep-roy / Safety-Detection-YOLOv8

It's a cutting-edge object detection model, to enhance safety measures by identifying and classifying objects related to personal protective equipment
MIT License
7 stars 3 forks source link

Where can i get your train dataset? #1

Closed ordioma closed 3 months ago

ordioma commented 4 months ago

Where can i get your train dataset?

biswadeep-roy commented 3 months ago

Thank you for your interest in the Safety Detection YOLOv8 project!

The project uses a pre-trained model (ppe.pt), so you do not need to train a dataset from scratch to use it. You can download the pre-trained model from the following link and place it in the project's root directory:

Download ppe.pt

If you are interested in training your own model or customizing the detection capabilities, you will need a dataset of images annotated with the objects you want to detect. Here are some steps and resources to get you started:

Collect Data: Gather images relevant to your use case (e.g., images of people wearing different types of PPE). Annotate Data: Use tools like LabelImg to label your images with bounding boxes around the objects of interest. Prepare Dataset: Organize your labeled data in a format compatible with YOLO training (e.g., COCO format or YOLO-specific format). Train the Model: Follow the YOLOv8 training instructions from the Ultralytics YOLOv8 repository to train your custom model. If you need more detailed guidance on any of these steps, feel free to ask!