app.py

### 1. Imports and class names setup ### 
import gradio as gr
import os
import torch

from torchvision import transforms
from timeit import default_timer as timer
from typing import Tuple, Dict


###  Model and transforms preparation ###

model = torch.load(f="smile_classifier.pth")

transform = transforms.Compose([
    transforms.CenterCrop(size=[178, 178]),
    transforms.Resize(size=[64, 64]),
    transforms.ToTensor()
])

### Predict function ###

# Create 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 = transform(img).unsqueeze(0)
    
    # Put model into evaluation mode and turn on inference mode
    model.eval()
    with torch.inference_mode():
        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
        pred_probs = model(img)[:, 0]
    
    # Create a prediction label and prediction probability dictionary for each prediction class (this is the required format for Gradio's output parameter)
    if pred_probs >= 0.5:
      pred_labels_and_probs = {"Smiling": f"{pred_probs.item()}"}
    else:
      pred_labels_and_probs = {"Not Smiling": f"{pred_probs.item()}"}
    
    # 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

### Gradio app ###

# Create title, description and article strings
title = "Smile Classifier 🙂😊😃"
description = "A Smile classifier computer vision model (trained on [celebA](https://pytorch.org/vision/main/generated/torchvision.datasets.CelebA.html) data) to classify images of people and identify if they are smiling or not."
article = "Please select an image from provided examples and submit, the model will predict if the person in the image \
is smiling or not and will also provide prediction probabilities."

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

#Create the Gradio demo
demo = gr.Interface(fn=predict, # mapping function from input to output
                    inputs=gr.Image(type="pil"), # what are the inputs?
                    outputs=[gr.Label(num_top_classes=2, label="Predictions"), # what are the outputs?
                             gr.Number(label="Prediction time (s)")], # our fn has two outputs, therefore we have two outputs
                    # Create examples list from "examples/" directory
                    examples=example_list, 
                    title=title,
                    description=description,
                    article=article)

# Launch the demo!
demo.launch()