app.py

### 1. Import and class names setup ###
import gradio as gr
import os
from pathlib import Path
import torch

from model import create_effnetb2_model
from time import perf_counter
from typing import Tuple, Dict

from PIL import Image
import torchvision

# Setup class names (hardcoded, these shall reside in a json file or sth like that...)
class_names = ["pizza","steak","sushi"]

### 2. Model and transforms preparation ###
effnetb2_model, effnetb2_transforms = create_effnetb2_model(num_classes=len(class_names))

# Load save weights
effnetb2_model.load_state_dict(torch.load(f="09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20percent.pth",
                                          map_location=torch.device("cpu"))) # map location to cpu is a must, as we have trained our model in the GPU

### 3. Predict function

def predict(img) -> Tuple[Dict,float]:
  # Start a timer
  start_time = perf_counter()

  # Transform the input image for use with EffNetB2
  effnetb2_transforms = torchvision.models.EfficientNet_B2_Weights.DEFAULT.transforms()
  img_tensor = effnetb2_transforms(img)

  # Put model in eval and inference
  effnetb2_model.eval()
  with torch.inference_mode():
    y_logits = effnetb2_model(img_tensor.unsqueeze(dim=0))
    y_pred_probs = torch.softmax(y_logits,dim=1)
    y_pred_probs_list = y_pred_probs.squeeze().tolist()
  
  # Creatae a prediction probability dictionary
  pred_prob_dict = {class_names[i]:float(prob) for i,prob in enumerate(y_pred_probs_list)}

  # End timer
  end_time = perf_counter()

  return pred_prob_dict, round(end_time-start_time,4)


### 4. Launch app

import gradio as gr

foodvision_mini_examples_path = "examples"

example_list = [str(path) for path in Path(foodvision_mini_examples_path).rglob("*.jpg")]

# Create title, description and article
title = "FoodVisionMini V0 🍕🍖🍣" + os.environ["test_ando_secret"]
description = "An <a href='https://pytorch.org/vision/main/models/generated/torchvision.models.efficientnet_b2.html#torchvision.models.efficientnet_b2'>EfficientNetB2</a> feature extractor computer vision model to classify images into pizza, steak or sushi<br>I have yet to improve it to label non-food images. Paciencia amigos"
article = "Created at <a href='#'>09_pytorch_model_deploy.ipynb</a> Google Colab notebook"

# Create the Gradio demo
demo = gr.Interface(fn=predict,
                    inputs=gr.Image(type="pil"),
                    outputs=[gr.Label(num_top_classes=3, label="predictions"),
                             gr.Number(label="Prediction time (s)")],
                    examples=example_list,
                    title=title,
                    description=description,
                    article=article)

# Launch the demo
demo.launch(share=True) # run on public url


# *** IMPORTANTE: The Flag button of the interface will create a folder named "flagged" that will contain the images and predictions of those images that someone has Flagged***