app.py

### 1. Import 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"),
        weights_only=True
    )
)

### 3. Predict fucntin ###
 
def predict(img) -> Tuple[Dict, float]:
  # Start a timer
  start_time = timer()
  # Transform the input image for use with EffNetB2
  transform_img = effnetb2_transforms(img).unsqueeze(0)

  # Put model into eval mode, main prediction
  effnetb2.eval()
  with torch.inference_mode():
    pred_prob=torch.softmax(effnetb2(transform_img),dim=1)

  # Create a prediction label and prediction probability dictionary
  pred_labels_and_probs = {class_names[i]:float(pred_prob[0][i]) for i in range(len(class_names))}
  
  # Calculate pred time
  time = round(timer()-start_time,4)

  # Return pred dict and pred time
  return pred_labels_and_probs,time


### 4. Gradio app ###

# Create title , description and article
title = "FoodVision Mini 🍕🥩🍣"
description = " An [EfficinetNetB2](https://pytorch.org/vision/main/models/generated/torchvision.models.efficientnet_b2.html) feature extractor computer vision model to classify images as pizza, steak, sushi"

# Create example list
example_list = [["examples/"+example] for example in os.listdir("examples")]


# Create the Graio demo
demo = gr.Interface(fn=predict, # maps inputs to ouputs
                    inputs=gr.Image(type="pil"),
                    outputs=[gr.Label(num_top_classes=3,label='Predictions'),
                            gr.Number(label="Predicition time (s)")],
                    examples=example_list,
                    title=title,
                    description=description,
                    cache_examples=True)

# Launch the demo!
demo.launch(debug=False )