app.py

### 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 Tuple, Dict

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

### 2. MOdel and transforms perparation ###
effnetb2, effnetb2_transforms = create_effnetb2_model(
    num_classes=3)

# 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
  img = effnetb2_transforms(img).unsqueeze(0) # unsqueeze = add batch dimension on 0th index

  # Put model into eval mode, make prediction
  effnetb2.eval()
  with torch.inference_mode():
    # Pass transformed image through the model and turn the prediction logit into probability
    pred_probs = torch.softmax(effnetb2(img), dim=1)

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

  # Calculate pred time
  end_time = timer()
  pred_time = round(end_time - start_time, 4)

  # Return pred dict and pred time
  return pred_labels_and_probs, pred_time

### 4. Gradio app ###

# Create title, description and article
title = "FoodVision Mini 🍕🥩🍣"
description = "An [EfficientNetB2 feature extractor](https://pytorch.org/vision/stable/models/generated/torchvision.models.efficientnet_b2.html#torchvision.models.efficientnet_b2) computer vision model to classify images as pizza, steak or 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 output
                    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) # Don't need share=True in HuggingFace