import gradio as gr
import os
from PIL import ImageOps
from torch.utils.benchmark import timer

example_list = [["examples/" + example] for example in os.listdir("examples")]
def processImage(img, text):
    """Transforms and performs a prediction on img and returns prediction and time taken.
    """
    # Start the timer
    start_time = timer()
    inverted_img = ImageOps.invert(img)
    text = "Hello" + text
    pred_labels_and_probs = "Pred props"
    # Calculate the prediction time
    pred_time = round(timer() - start_time, 5)

    # Return the prediction dictionary and prediction time
    return inverted_img, pred_labels_and_probs, pred_time, text


# Create title, description and article strings
title = "FoodRecognition  🍕🥩🍣"
description = "An EfficientNetB2 model to classify images of food as pizza, steak or sushi."
article = "Created at my."

# Create the Gradio demo
demo = gr.Interface(fn=processImage,  # mapping function from input to output
                    inputs=[gr.Image(type="pil"), gr.Textbox()],
                    outputs=[gr.Image(type="pil"), gr.Label(label="Process image"),  # what are the outputs?
                             gr.Number(label="Prediction time (s)"), gr.Textbox(label="Result")],
                    # our fn has two outputs, therefore we have two outputs
                    # examples=example_list,
                    title=title,
                    description=description,
                    article=article,
                    examples=example_list)

# Launch the demo!
demo.launch(debug=False,  # print errors locally?
            share=True)  # generate a publically shareable URL?