https://github.com/saritaphd/multi-class-image-classification-using-yolov5
This project implements a Multi-Class Image Classification model using YOLOv5, a state-of-the-art deep learning architecture for object detection and classification. The model is trained to recognize multiple classes of objects in images, providing accurate classification and bounding box predictions.
https://github.com/saritaphd/multi-class-image-classification-using-yolov5
Last synced: 9 days ago
JSON representation
This project implements a Multi-Class Image Classification model using YOLOv5, a state-of-the-art deep learning architecture for object detection and classification. The model is trained to recognize multiple classes of objects in images, providing accurate classification and bounding box predictions.
- Host: GitHub
- URL: https://github.com/saritaphd/multi-class-image-classification-using-yolov5
- Owner: SaritaPhD
- License: mit
- Created: 2024-10-20T16:56:39.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2024-12-08T06:58:44.000Z (7 months ago)
- Last Synced: 2025-04-09T00:29:01.269Z (3 months ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 1.91 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Multi-Class-Image-Classification-using-YOLOv5
This project implements a Multi-Class Image Classification model using YOLOv5, a state-of-the-art deep learning architecture for object detection and classification. The model is trained to recognize multiple classes of objects in images, providing accurate classification and bounding box predictions. The dataset used for training consists of labeled images across different categories, enabling the model to generalize well to unseen data. YOLOv5's efficiency and real-time performance make it an ideal choice for various image classification tasks, including object detection and localization.
## Key Features:
- Multi-Class Classification: Classify images into multiple categories.
- Real-Time Object Detection: Predict class labels and bounding boxes in real-time.
- Easy Customization: Modify the dataset and retrain the model for different classification tasks.