app.py

# 1. Imports and class names 
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 

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

# 2. Model and transforms preparations 
# Create model 
effnetb2, effnetb2_transforms = create_effnetb2_model(num_classes=101) 

# Load saved weights 
effnetb2.load_state_dict(
    torch.load(
        f="09_pretrained_effnetb2_feature_extractor_food101_20_percent.pth",
        map_location=torch.device("cpu") # load to CPU
    )
)

# 3. Predict function 

# Create predict function
def prdict(img) -> Tuple[Dict, float]: 
  """
  Transforms and performs a prediction on img and returns predictions and time per prediction
  """

  # Start the timer 
  start_time = timer() 

  # Transform the target image and add a batch dimension
  img = effnetb2_transforms(img).unsqueeze(0)

  # Put the model into evaluation mode and turn on inference mode
  effnetb2.eval() 
  with torch.inference_mode():
    # Pass the transformed iamge through the model and turn the prediction logits into prediction probablities 
    pred_probs = torch.softmax(effnetb2(img), dim=1) 

  # Create a prediction label and prediction probability dictionary for each prediction class (required format for Gradio)
  pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}

  # Calculate prediction time
  pred_time = round(timer() - start_time, 5)

# 4. Gradio app 

# Create title, description and article strings
title = "FoodVision Big"
description = "An EfficientNetB2 feature extractor computer vision model to classify images of food into [101 different classes](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/extras/food101_class_names.txt)."
article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/) course."

# 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()