app.py

import torch
import datasets
from transformers import AutoFeatureExtractor, AutoModelForImageClassification
import gradio as gr

dataset = datasets.load_dataset('beans', 'full_size')

extractor = AutoFeatureExtractor.from_pretrained("saved_model_files")
model = AutoModelForImageClassification.from_pretrained("saved_model_files")

labels = dataset['train'].features['labels'].names

def classify(im):
  features = extractor(im, return_tensors='pt')
  logits = model(features["pixel_values"])[-1]
  probability = torch.nn.functional.softmax(logits, dim=-1)
  probs = probability[0].detach().numpy()
  confidences = {label: float(probs[i]) for i, label in enumerate(labels)} 
  return confidences

interface = gr.Interface(
    fn=classify,
    inputs="image",
    outputs="label",
    examples=[
        'https://datasets-server.huggingface.co/assets/beans/--/default/train/5/image/image.jpg',
        'https://datasets-server.huggingface.co/assets/beans/--/default/train/10/image/image.jpg',
        'https://datasets-server.huggingface.co/assets/beans/--/default/train/15/image/image.jpg'
    ],
    title="bean leaf classification",
    description="Input an image of a bean leaf to predict whether it is healthy or diseased.",
)

interface.launch()