app.py

### 1. 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
class_names = ['1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z']

### 2. Model and transforms preparation ###

# Create EffNetB2 model
effnetb2, effnetb2_transforms = create_effnetb2_model(
    num_classes=35, # len(class_names) would also work
)

# Load saved weights
effnetb2.load_state_dict(
    torch.load(
        f="ISL.pth",
        map_location=torch.device("cpu"),  # load to CPU
    )
)

### 3. Predict function ###

# Create predict function
def predict(img) -> Tuple[Dict, float]:
    """Transforms and performs a prediction on img and returns prediction and time taken.
    """
    # Start the timer
    start_time = timer()
    img=img.convert('RGB')
    # Transform the target image and add a batch dimension
    img = effnetb2_transforms(img).unsqueeze(0)

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

    # Create a prediction label and prediction probability dictionary for each prediction class (this is the required format for Gradio's output parameter)
    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 and prediction time
    return pred_labels_and_probs, pred_time

### 4. Gradio app ###


# Create title, description and article strings
title = "INDIAN SIGN LANGUAGE DETECTOR"
description = "An EfficientNetB2 feature extractor computer vision model to classify images of INDIAN SIGN LANGUAGE ."
#article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/)."

# Create the Gradio demo
demo = gr.Interface(fn=predict, # mapping function from input to output
                    inputs=gr.Image(type="pil"), # what are the inputs?
                    outputs=[gr.Label(num_top_classes=3, label="Predictions"), # what are the outputs?
                             gr.Number(label="Prediction time (s)")], # our fn has two outputs, therefore we have two outputs
                    examples=['711.jpg','939.jpg','1017.jpg'],
                    title=title,
                    description=description,
                    )

# Launch the demo!
demo.launch()