# pip install -U transformers accelerate
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("sofiane-isi/vit-beans-sofiane")
model = AutoModelForImageClassification.from_pretrained("sofiane-isi/vit-beans-sofiane", device_map="auto")Quick Links
ViT Beans Classifier
Vision Transformer fine-tuned for bean leaf disease classification.
Repository
sofiane-isi/vit-beans-sofiane
Dataset
AI-Lab-Makerere/beans
Classes:
- angular_leaf_spot
- bean_rust
- healthy
Evaluation
- Accuracy: 0.96875
- Evaluation loss: 0.12236211448907852
Base model
google/vit-base-patch16-224-in21k
MLOps workflow
Dataset → preprocessing → fine-tuning → evaluation → Hugging Face Hub → Model Card → Space.
Limitations
Educational model fine-tuned specifically on the Beans dataset.
- Downloads last month
- 6
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="sofiane-isi/vit-beans-sofiane") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")