### 1. Imports and class names setup ###
import gradio as gr
import os
import torch
from model import create_effnetb2_model
from timeit import default_timer as timer
from typing import Dict, Tuple


# Setup class names
class_names = ['pizza', 'steak', 'sushi']

### 2. Model and transforms perparation ###
effnetb2, effnetb2_transforms = create_effnetb2_model()

# Load save weights
effnetb2.load_state_dict(torch.load(f='09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth',
                                    map_location=torch.device('cpu')))  # load the model to the CPU

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

    # Transform the input image for use with EffNetB2
    transformed_img = effnetb2_transforms(img).unsqueeze(dim=0)  # unsqueeze = add batch dimension on 0th

    # Put model into eval mode, make prediction
    with torch.inference_mode():
        effnetb2.eval()
        
        # Pass the transformed image through the model and turn the prediction logits into probabilities
        pred_prob = effnetb2(transformed_img).softmax(dim=1)

    # Create a prediction label and prediction probability dictionary
    pred_labels_and_probs = {class_names[i]: pred_prob[0][i].item() for i in range(len(class_names))}

    # Calcualte pred time
    end_time = timer()
    inference_time = round(end_time - start_time, 4)

    # Return pred dict and pred time
    return pred_labels_and_probs, inference_time

### 4. Gradio app ###
# Create title, description and aritcle
title = 'FoodVision Mini 🍕🥩🍣'
description = 'An [EfficientNetB2 feature extractor](https://pytorch.org/vision/0.16/models/generated/torchvision.models.efficientnet_b2.html#efficientnet-b2) computer vision model to classify images as pizza, steak, sushi.'
article = 'Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/#74-building-a-gradio-interface).'

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

# Create the Gradio demo
demo = gr.Interface(fn=predict,  # maps inputs to outputs
                    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)

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