model_name: Crop Anomaly Detection Model - 3 Class
tags:
- pytorch
- resnet50
- agriculture
- anomaly-detection
- wheat
- plant-disease
license: apache-2.0
library_name: transformers
datasets:
- Crop-disease-dataset
model_type: resnet50
num_classes: 3
classes:
- fall armyworm
- p_def
- blb
preprocessing:
resize: 256
center_crop: 224
normalize:
- 0.485
- 0.456
- 0.406
normalize_std:
- 0.229
- 0.224
- 0.225
framework: pytorch
task: image-classification
pipeline_tag: image-classification
Wheat Anomaly Detection Model
Overview
This is a ResNet50-based image classification model designed for wheat anomaly detection. It classifies images into three categories:
Fall Armyworm (fa)
Phosphorus Deficiency (p_def)
Bacterial Leaf Blight (blb)
The model has been fine-tuned on an agricultural dataset and optimized for accurate detection of these anomalies.
Model Performance
Validation Accuracy: 93.82%
Class-wise Accuracy:
Fall Armyworm: 100.00%
Phosphorus Deficiency: 86.21%
Bacterial Leaf Blight: 95.00%
Installation
Ensure you have transformers, torch, and gradio installed:
Usage
Here is an example of how to load and use the model for prediction using PyTorch:
Dataset
The model was trained using the Wheat Disease Dataset with balanced classes. Ensure your images are resized to 224x224 and normalized using the provided values.
License
This model is licensed under the Apache-2.0 License. You are free to use, modify, and distribute it under the terms of the license.