app.py

import datasets
from datasets import load_dataset
import gradio as gr
import torch
from transformers import Trainer, TrainingArguments
from transformers import AutoModelForImageClassification
import numpy as np
from transformers import AutoFeatureExtractor, AutoModelForImageClassification

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

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

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


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

# Run the Gradio interface for the app
interface = gr.Interface(
    fn=classify,
    inputs=["image"], 
    outputs=["label"],
    title="Leaf disaease classifier",
    description="A pre-trained vit model for classifying leaf diseases"
)

interface.launch(debug=True)