app.py

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

from model import create_effnetb0_model
from timeit import default_timer as timer
from typing import Tuple, Dict

# Setup class names
class_names = ["eugene_h_krabs", "gary_the_snail", "karen_plankton", "mrs_puff", "patrick_star", "pearl_krabs", "sandy_cheeks", "sheldon_j_plankton", "spongebob_squarepants", "squidward_tentacles"]

### Model and transforms preparation ###
# Create EffNetB0 model
effnetb0, effnetb0_transforms = create_effnetb0_model(
    num_classes=10
)

# Load saved weights
effnetb0.load_state_dict(
    torch.load(
        f="model_efficientnet_b0.pth",
        map_location=torch.device("cpu")
    )
)

### 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 = effnetb0_transforms(img).unsqueeze(dim=0)

  # Put model into evaluation mode and turn on inference mode
  effnetb0.eval()
  with torch.inference_mode():
    # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
    pred_probs = torch.softmax(effnetb0(img), dim=1)

  # Create a prediction label and prediction probability dictionary for each prediction class (required format for Gradio's output parameter)
  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)

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

### Gradio app ###
title = "Spongebob Character Identifier 🧽👖🐙🦀🐿️🍍🍔🐳🖥️"
description = "An EfficientNetB0 feature extractor computer vision model to classify between 10 character from Spongebob Squarepants: Spongebob, Patrick, Squidward, Gary, Mr. Krabs, Mrs.Puff, Sandy, Plankton, Karen, and Pearl"
article = "Read more at: [Spongebob Character Identifier](https://gulnuravci.github.io/scripts/project_pages/spongebob_character_identifier/spongebob_identifier.html)"

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

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=10, label="Predictions"), # what are the outputs?
                             gr.Number(label="Prediction time (s)")], # our fn has two outputs, therefore we have two outputs
                    examples=example_list,
                    title=title,
                    description=description,
                    article=article)

demo.launch()