import gradio as gr

import tensorflow as tf
import cv2
import numpy as np


# Load the saved model
model = tf.keras.models.load_model('model/cnn_9_layer_model.h5')

# Define the face cascade and emotions
face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
emotions = ['Angry', 'Disgust', 'Fear', 'Happy', 'Sad', 'Surprise', 'Neutral']

# Define the predict_emotion function
def predict_emotion(frame):
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray, 1.3, 5)
    for (x, y, w, h) in faces:
        face = gray[y:y+h, x:x+w]
        face = cv2.resize(face, (48, 48))
        face = np.expand_dims(face, axis=-1)
        face = np.expand_dims(face, axis=0)
        prediction = model.predict(face)
        emotion = emotions[np.argmax(prediction)]
        cv2.putText(frame, emotion, (x, y-10), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
        cv2.rectangle(frame, (x, y), (x+w, y+h), (255, 0, 0), 2)
    return frame

# Start the video capture and emotion detection
# cap = cv2.VideoCapture(0)
# while True:
#     ret, frame = cap.read()
#     if ret:
#         frame = predict_emotion(frame)
#         cv2.imshow('Live Facial Emotion Detection', frame)
#     if cv2.waitKey(1) == ord('q'):
#         break
# cap.release()
# cv2.destroyAllWindows()


input_image = gr.inputs.Image(source = "webcam")
# video = gr.inputs.Video(source = "webcam" )

output_image = gr.inputs.Image(type = "numpy", label="Emotion Detection" )



iface = gr.Interface(
	fn = predict_emotion, 
	inputs=input_image, 
	outputs=output_image,
	# interpretation = "default",
	title = "Mood Detectives",
	description = "Real-Time Emotion Detection\nDetects Angry, Happy, Sad, Fear, Disgust, Surprise, Neutral Facial Expressions"
	)

iface.launch()