app.py

from sentence_transformers import util,SentenceTransformer
model = SentenceTransformer('clip-ViT-L-14')

def predict(im1, im2,inp_sim):
  img_emb = model.encode([im1, im2])
  sim = util.cos_sim(img_emb[0], img_emb[1])
  if sim > inp_sim:
    return sim, "SAME PERSON, UNLOCK PHONE"
  else:
    return sim, "DIFFERENT PEOPLE, DON'T UNLOCK"

import gradio as gr
description = "An application that can recognize if two faces belong to the same person or not"
title = "Facial Identity Recognition System"

interface = gr.Interface(fn=predict, 
                         inputs= [gr.Image(type="pil", source="webcam"), 
                                  gr.Image(type="pil"),
                                  gr.Slider(0, 1, value=0.8, label="Similarity Percentage", info="Choose betwen 0 and 1")], 
                         outputs= [gr.Number(label="Similarity"),
                                   gr.Textbox(label="Message")]
                         )

interface.launch(debug=True)