app.py

import gradio as gr

import os
import cv2
import numpy as np
from keras.preprocessing import image
import warnings
warnings.filterwarnings("ignore")
from keras_preprocessing.image import ImageDataGenerator
from keras.utils import img_to_array, load_img
from keras.models import  load_model
import matplotlib.pyplot as plt
import numpy as np
from PIL import Image
import tensorflow as tf

# load model
model = load_model(r'best_model.h5')

face_haar_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

def analyze_emotion(frame):
    gray_img = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
    faces_detected = face_haar_cascade.detectMultiScale(gray_img, 1.32, 5)

    for (x, y, w, h) in faces_detected:
        cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), thickness=7)
        roi_gray = gray_img[y:y + w, x:x + h]  # cropping region of interest i.e. face area from  image
        roi_gray = cv2.resize(roi_gray, (224, 224))
        img_pixels = tf.keras.preprocessing.image.img_to_array(roi_gray)
        img_pixels = np.expand_dims(img_pixels, axis=0)
        img_pixels /= 255

        predictions = model.predict(img_pixels)

        # find max indexed array
        max_index = np.argmax(predictions[0])

        emotions = ('angry', 'disgust', 'fear', 'happy', 'sad', 'surprise', 'neutral')
        predicted_emotion = emotions[max_index]

        cv2.putText(frame, predicted_emotion, (int(x), int(y)), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)

    return frame[...,::-1]

inputs = gr.inputs.Video(source="webcam")
outputs = gr.outputs.Image(type="numpy")

iface = gr.Interface(fn=analyze_emotion, inputs=inputs, outputs=outputs, title="Facial Emotion Analysis",
             description="Detects emotions in real-time from webcam video input")

iface.launch()