import gradio as gr
import os
import torch

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

# Setup class names
with open("class_names.txt", "r") as f:
  class_names = [food_name.strip() for food_name in f.readlines()]

# Create model
vit, vit_transforms = create_vit_model(num_classes=101)

# Load trained model weights
vit.load_state_dict(
    torch.load(
        f="pretrained_vit_feature_extractor_food101_finetuned.pth",
        map_location=torch.device("cpu")
    )
)

# Predict function
def predict(img) -> Tuple[Dict, float]:
    """
    Transforms and performs a prediction on img and returns prediction and time taken.
    """
    # Start the timer
    start_time = timer()
    
    # Transform the target image and add a batch dimension
    img = vit_transforms(img).unsqueeze(0)
    
    # Put model into evaluation mode and turn on inference mode
    vit.eval()
    with torch.inference_mode():
        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
        pred_probs = torch.softmax(vit(img), dim=1)
    
    # Create a prediction label and prediction probability dictionary for each prediction class
    pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
    
    # Calculate the prediction time
    pred_time = round(timer() - start_time, 5)
    
    # Return the prediction dictionary and prediction time 
    return pred_labels_and_probs, pred_time

# Create title, description and article strings
title = "FoodVision"
description = "A ViT feature extractor computer vision model to classify images of food into [101 different classes](https://huggingface.co/datasets/ethz/food101)."
article = "[Pretrained ViT model](https://arxiv.org/abs/2010.11929) finetuned on Food101 dataset"

# Create examples list from "examples/" directory
example_list = [["examples/" + example] for example in os.listdir("examples")]

# Create Gradio interface 
demo = gr.Interface(
    fn=predict,
    inputs=gr.Image(type="pil"),
    outputs=[
        gr.Label(num_top_classes=5, label="Predictions"),
        gr.Number(label="Prediction time (s)"),
    ],
    examples=example_list,
    title=title,
    description=description,
    article=article,
)

# Launch the app!
demo.launch()