app.py

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

with open("class_names.txt", "r") as f:
    class_names = [food_name.strip() for food_name in f]

effnetb2, effnetb2_transforms = create_effnetb2_model()

effnetb2.load_state_dict(
    torch.load(
        f="effnetb2_food101_complete_dataset.pth",
        map_location=torch.device("cpu"),
        weights_only=True
    )
)


def predict(img) -> Tuple[Dict, float]:
    start_time = timer()
    img = effnetb2_transforms(img).unsqueeze(0)

    effnetb2.eval()
    with torch.inference_mode():
        pred_probs = torch.softmax(effnetb2(img), dim=1)

    # create a prediction label in gradio format
    pred_labels_and_probs = {class_names[i]: float(
        pred_probs[0][i]) for i in range(len(class_names))}

    pred_time = round(timer() - start_time)

    return pred_labels_and_probs, pred_time


# 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/Victoran0/foodvision-bigdataset/demos/foodvision_big/class_names.txt).."
article = "You can find the full source code at (https://github.com/Victoran0/foodvision-bigdataset)."

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
)

demo.launch()