from transformers import ViTImageProcessor, ViTForImageClassification
from PIL import Image
import torch

# Load model and processor
processor = ViTImageProcessor.from_pretrained("ssevan/ug-food-detector")
model = ViTForImageClassification.from_pretrained("ssevan/ug-food-detector")

# Process image
image = Image.open('food_image.jpg')
inputs = processor(image, return_tensors='pt')

# Get predictions
with torch.no_grad():
    outputs = model(**inputs)
    probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
    predicted_class_idx = torch.argmax(probabilities, dim=1).item()

print(f'Predicted class index: {predicted_class_idx}')

Mobile Usage

This model is optimized for mobile deployment.