Downloads · 30 days
0
PlantDiseaseDetection
liriope/PlantDiseaseDetection
PlantDiseaseDetection is a image classification model from liriope. Use it when you need a label for an image. It is set up for keras. The card lists the license as mit.
This project leverages EfficientNetB4, a state-of-the-art convolutional neural network (CNN), to classify plant diseases using the PlantVillage dataset. The trained model achieves 97.66% accuracy on the test set, demo…
Access
Public
Updated Apr 15, 2025
Repo size
98 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.h598 MB · 100%
At a glance
- Task
- Image Classification
- Library
- keras
- License
- mit
- Access
- Public
- Created
- Apr 10, 2025
- Updated
- Apr 15, 2025
- SHA
- 1f17a46c
Base models
Datasets
Spaces
Model card
From the Hugging Face model README
Plant Disease Classification with EfficientNetB4
Overview
This project leverages EfficientNetB4, a state-of-the-art convolutional neural network (CNN), to classify plant diseases using the PlantVillage dataset. The trained model achieves 97.66% accuracy on the test set, demonstrating robust performance in identifying crop diseases from leaf images.
Key Features
High Accuracy: 97.66% test accuracy, outperforming many traditional CNN architectures. Efficient Architecture: EfficientNetB4 balances computational efficiency and model capacity, making it suitable for deployment. Scalability: Adaptable to other plant disease datasets or extended to new disease classes.
Dataset
The model is trained on the PlantVillage dataset, which contains 54,305 images of healthy and diseased leaves across 14 crop species and 38 disease classes. Images are resized to 380x380 pixels to match EfficientNetB4’s input dimensions.
- Task
- Image Classification
- Library
- keras
- License
- mit
- Created
- Apr 10, 2025
- Updated
- Apr 15, 2025