app.py

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

# Model and transforms preparation
# 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'))
)

# prediction functions
# create predict functions
def predict(img) -> Tuple[Dict, float]:
  # start the timer 
  start_time = timer()

  # transform the image and add the batch dimension
  img = effnetb2_transforms(img).unsqueeze(0)

  # put the model into evaluation mode and turn on the inference mode
  effnetb2.eval()
  with torch.inference_mode():
    # pass the transformed image through the model and turn the prediction
    pred_probs = torch.softmax(effnetb2(img), dim=1)

  # create prediction label and probabilities dictionary (necessary for gradio)
  pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}

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

  # return the prediction dictionary
  return pred_labels_and_probs, pred_time

# gradio app
# create title, description and article string
title = 'Foodvision BIG'
description = 'An EfficientNetB2 feature extractor computer vision model to classifiy Food101 datasets images'
article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/)."

# create exmaple list from example dictionary
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()