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

dataset = datasets.load_dataset("beans")

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

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


def classify(im: gr.inputs.Image) -> dict:
    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",
                         title="Bean classifier",
                         description="Web-application that can take in an image of a bean leaf and predict whether it is healthy or diseased",
                         examples = ['./images/img_0.png'])
interface.launch(debug=True)