app.py

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

from model import create_effnetb2_model
from timeit import default_timer as timer

# Setup 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 preparation ###
# Create model and transforms
effnetb2, effnetb2_transforms = create_effnetb2_model(
    num_classes=len(class_names),
)

# Load save weights
effnetb2.load_state_dict(torch.load('09_pretrained_effnetb2_feature_extractor_food101_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(dim=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 logits into probabilities
        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 BIG 🍔👁💪"
descripton = "An EfficientNetB2 Feature Extractor computer vision model to classify 101 classes of food from the Food101 dataset."
article = "Created at 09. PyTorch Model Deployment."

# 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=5, label="Predictions"),
                             gr.Number(label="Prediction time (s)")],
                    examples=example_list,
                    title=title,
                    description=descripton,
                    article=article)

# Launch Demo!
demo.launch()