metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - beans
metrics:
  - accuracy
model-index:
  - name: vit-base-beans-demo-v5
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: beans
          type: beans
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 1

Fine-Tuned ViT for Beans Leaf Disease Classification

Model Information

Model Name: VIT_Beans_Leaf_Disease_Classifier
Base Model: Google/ViT-base-patch16-224-in21k
Task: Image Classification (Beans Leaf Disease Classification)
Dataset: Beans leaf dataset with images of diseased and healthy leaves.

Problem Statement

The goal of this model is to classify leaf images into three categories:

{
  "angular_leaf_spot": 0,
  "bean_rust": 1,
  "healthy": 2,
}

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1495	1.54	100	0.0910	0.9774
0.0121	3.08	200	0.0155	1.0

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3

Get Started With The Model:

! pip -q  install datasets transformers[torch]


from transformers import pipeline
from PIL import Image

# Use a pipeline as a high-level helper

pipe = pipeline("image-classification", model="ayoubkirouane/VIT_Beans_Leaf_Disease_Classifier")

# Load the image

image_path = "Your image_path "
image = Image.open(image_path)

# Run inference using the pipeline
result = pipe(image)

# The result contains the predicted label and the corresponding score
predicted_label = result[0]['label']
confidence_score = result[0]['score']

print(f"Predicted Label: {predicted_label}")
print(f"Confidence Score: {confidence_score}")