import gradio as gr
import os
import torch

from model import create_effnetb2_model
from timeit import default_timer as timer
from typing import Tuple, Dict

class_names = ['cat', 'dog', 'pizza', 'steak', 'sushi']

effnetb2, effnetb2_transforms = create_effnetb2_model(num_classes=5)

effnetb2.load_state_dict(
    torch.load(
        f="Mult-class_classifier_98_percent_accuracy.pth",
        map_location=torch.device("cpu") # load the model to the CPU
    )
)

def predict(img) -> Tuple[Dict, float]:
  # Start a timer
  start_time = timer()

  img = effnetb2_transforms(img).unsqueeze(0)

  effnetb2.eval()
  with torch.inference_mode():
    pred_probs = torch.softmax(effnetb2(img), dim=1)

  pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}

  end_time = timer()
  pred_time = round(end_time - start_time, 4)

  return pred_labels_and_probs, pred_time


title = "Image classification 🐈🐕🍕🥩🍣"
description = "An computer vision model to classify images as cat, dog, pizza, steak or sushi."
article = "Image classification"

example_list = [["examples/" + example] for example in os.listdir("examples")]

demo = gr.Interface(fn=predict,
                    inputs=gr.Image(type="pil"),
                    outputs=[gr.Label(num_top_classes=3, label="Predictions"),
                             gr.Number(label="Prediction time (s)")],
                    examples=example_list,
                    title=title,
                    description=description,
                    article=article)

demo.launch()