import datasets
import torch
from transformers import AutoFeatureExtractor, AutoModelForImageClassification

dataset =  datasets.load_dataset('beans') # This should be the same as the first line of Python code in this Colab notebook

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

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

def classify(im):
  features = feature_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

import gradio as gr

Instruction = "Browse the internet to search and download bean-leaf images with different leaf conditions"
title="Bean-leaf-disease Image classification demo"
description = "Drop an Input image to classify, Observe the model prediction across 3 distinct categories."
article = """
            - Select an image from the examples provided as demo image
            - Click submit button to make Image classification
            - Click clear button to try new Image for classification
          """

interface = gr.Interface(
    classify,
    inputs='image',
    outputs='label',
    instructuction = Instruction,
    title = title,
    description = description,
    article = article,
    examples=["example-image1.jpg",
              "example-image2.jpg",
              "example-image3.jpeg"]
    )

interface.launch(debug=True)