import transformers
import torch
from datasets import load_dataset, Image
from transformers import AutoFeatureExtractor, AutoModelForImageClassification, ViTImageProcessor, ViTForImageClassification

image_processor = ViTImageProcessor.from_pretrained('google/vit-base-patch16-224')
extractor = AutoFeatureExtractor.from_pretrained("saved_model_files")
model = AutoModelForImageClassification.from_pretrained("saved_model_files")

labels = ['affected', 'destroyed', 'no_damage']

def classify(im):
  features = image_processor(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

interface = gr.Interface(
    fn=classify,
    inputs="image",
    outputs="label"
  )

interface.launch(share=True, debug=True)