app.py

from custom_torch_module.deploy_utils import Onnx_deploy_model
import gradio as gr
import time
from PIL import Image
import os
from pathlib import Path

model_path = list(Path("deploying model/").glob("*.onnx"))[0]
input_size = [1, 3, 224, 224]
img_size = input_size[-1]

title = "Gender Vision mini"
description = "An resnet50_clip_gap based model(fine tuned with Custom dataset : around 800 train images & 200 test iamges) F1 Score : 100%(1.00) with the custom test dataset. Optimized with ONNX(around 1.7 times faster than PyTorch version on cpu)"
article = "Through bunch of fine tuning and experiments. !REMEMBER! This model can be wrong."

def predict(img):
    start_time = time.time()
    output = onnx_model.run(img, return_prob=True)
    end_time = time.time()
    elapsed_time = end_time - start_time
    prediction_fps = 1 / elapsed_time
    
    pred_label_and_probs = {"Men" : output[0],"Women" : output[1]}

    return pred_label_and_probs, prediction_fps

onnx_model = Onnx_deploy_model(model_path=model_path, img_size=img_size)
example_list = [["examples/" + example] for example in os.listdir("examples")]

# Create the Gradio demo
demo = gr.Interface(fn=predict, 
                    inputs=gr.Image(type="pil"),
                    outputs=[gr.Label(num_top_classes=2, label="Predictions"),
                             gr.Number(label="Prediction speed(FPS)")], 
                    examples=example_list,
                    title=title,
                    description=description,
                    article=article)

# Launch the demo
demo.launch()