Instructions to use Mehfooz08/AgriSenAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use Mehfooz08/AgriSenAI with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://Mehfooz08/AgriSenAI") - Notebooks
- Google Colab
- Kaggle
π± Plant Disease Detection β MobileNetV2
A deep learning image-classification model for detecting plant diseases from leaf images.
The model uses MobileNetV2 and was trained on the PlantVillage dataset covering 9 crop species and 29 disease/healthy classes.
π€ Model
Architecture: MobileNetV2
Task: Image Classification
Framework: TensorFlow / Keras
Number of Classes: 29
Crop Species: 9
Supported Crops
- Apple
- Bell Pepper
- Cherry
- Corn (Maize)
- Grape
- Peach
- Potato
- Strawberry
- Tomato
π Model Performance
The model achieved 97%+ testing accuracy on the evaluation data used in the project.
Performance reported here is based on the project's test evaluation. Real-world performance may differ when images contain different lighting conditions, backgrounds, camera quality, crop varieties, or diseases not represented in the training dataset.
π Prediction Pipeline
Plant Leaf Image
β
Image Preprocessing
β
MobileNetV2
β
Feature Extraction
β
Classification
β
Predicted Disease
β
Confidence Score
- Downloads last month
- -