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.readlines()]

effnetb2, effnetb2_transforms=create_effnetb2_model(
    num_classes=101
)

effnetb2.load_state_dict(
    torch.load(
        f="foodvision_big.pth",
        map_location=torch.device("cpu")
    )
)

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)

    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,5)
    return pred_labels_and_probs, pred_time


title="FoodVision Big"
description="Images of food as an input and the image class as output using efficient net b2"


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
)

# Launch the app!
demo.launch()