app.py

# import gradio as gr
# import os
# import cv2
# import numpy as np
# import imutils
# from keras.preprocessing.image import img_to_array
# from keras.models import load_model

# # Load the pre-trained models and define parameters
# detection_model_path = 'haarcascade_files/haarcascade_frontalface_default.xml'
# emotion_model_path = 'model4_0.83/model4_entire_model.h5'
# face_detection = cv2.CascadeClassifier(detection_model_path)
# emotion_classifier = load_model(emotion_model_path, compile=False)
# EMOTIONS = ['neutral', 'happiness', 'surprise', 'sadness', 'anger', 'disgust', 'fear', 'contempt', 'unknown']


# # face_detector_mtcnn = MTCNN()
# classifier = load_model(emotion_model_path)

# def predict_emotion(frame):
#     frame = imutils.resize(frame, width=300)
#     gray = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
#     faces = face_detection.detectMultiScale(gray, scaleFactor=1.1,
#                                             minNeighbors=5, minSize=(30, 30),
#                                             flags=cv2.CASCADE_SCALE_IMAGE)

#     for (fX, fY, fW, fH) in faces:
#         # Extract the ROI of the face from the grayscale image, resize it to a fixed 28x28 pixels, and then prepare
#         # the ROI for classification via the CNN
#         roi = gray[fY:fY + fH, fX:fX + fW]
#         roi = cv2.resize(roi, (48, 48))
#         roi = roi.astype("float") / 255.0
#         roi = img_to_array(roi)
#         roi = np.expand_dims(roi, axis=0)

#         preds = emotion_classifier.predict(roi)[0]
#         label = EMOTIONS[preds.argmax()]

#         # Overlay a box over the detected face
#         cv2.putText(frame, label, (fX, fY - 10),
#                     cv2.FONT_HERSHEY_DUPLEX, 0.5, (238, 164, 64), 1, cv2.LINE_AA)
#         cv2.rectangle(frame, (fX, fY), (fX + fW, fY + fH),
#                       (238, 164, 64), 2)

#     return frame





# demo = gr.Interface(
#     fn = predict_emotion,
#     inputs = gr.Image(type="numpy"),
#     outputs = gr.Image(),
#     # gr.components.Image(label="Predicted Emotion"),
#     # gr.components.Label(num_top_classes=2, label="Top 2 Probabilities")
#     #flagging_options=["blurry", "incorrect", "other"],
#     examples = [
        
#         os.path.join(os.path.dirname(__file__), "images/chandler.jpeg"),
#         os.path.join(os.path.dirname(__file__), "images/janice.jpeg"),
#         os.path.join(os.path.dirname(__file__), "images/joey.jpeg"),
#         os.path.join(os.path.dirname(__file__), "images/phoebe.jpeg"),
#         os.path.join(os.path.dirname(__file__), "images/rachel_monica.jpeg"),
#         os.path.join(os.path.dirname(__file__), "images/ross.jpeg"),
#         os.path.join(os.path.dirname(__file__), "images/gunther.jpeg")
     
#     ],
#     title = "How are you feeling?",
#     theme = "shivi/calm_seafoam"
# )
    


# if __name__ == "__main__":
#     demo.launch()
    
######################################################################################################################################################
import gradio as gr
import os
import cv2
import numpy as np
import imutils
from keras.preprocessing.image import img_to_array
from keras.models import load_model

# Load the pre-trained models and define parameters
detection_model_path = 'haarcascade_files/haarcascade_frontalface_default.xml'
emotion_model_path = 'model4_0.83/model4_entire_model.h5'
face_detection = cv2.CascadeClassifier(detection_model_path)
emotion_classifier = load_model(emotion_model_path, compile=False)
EMOTIONS = ['neutral', 'happiness', 'surprise', 'sadness', 'anger', 'disgust', 'fear', 'contempt', 'unknown']

# Define a function to process each frame for emotion prediction
def predict_emotion(frame):
    frame = imutils.resize(frame, width=300)
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    faces = face_detection.detectMultiScale(gray, scaleFactor=1.1,
                                            minNeighbors=5, minSize=(30, 30),
                                            flags=cv2.CASCADE_SCALE_IMAGE)

    for (fX, fY, fW, fH) in faces:
        roi = gray[fY:fY + fH, fX:fX + fW]
        roi = cv2.resize(roi, (48, 48))
        roi = roi.astype("float") / 255.0
        roi = img_to_array(roi)
        roi = np.expand_dims(roi, axis=0)
        preds = emotion_classifier.predict(roi)[0]
        label = EMOTIONS[preds.argmax()]
        cv2.putText(frame, label, (fX, fY - 10),
                    cv2.FONT_HERSHEY_DUPLEX, 0.5, (238, 164, 64), 1, cv2.LINE_AA)
        cv2.rectangle(frame, (fX, fY), (fX + fW, fY + fH),
                      (238, 164, 64), 2)
    return frame

# Define a function to process video input and output
def process_video(input_video_path, output_video_path):
    # Open the video capture
    cap = cv2.VideoCapture(input_video_path)
    # Get video properties (dimensions, frame rate)
    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
    fps = cap.get(cv2.CAP_PROP_FPS)
    # Define video writer for output
    out = cv2.VideoWriter(output_video_path, cv2.VideoWriter_fourcc(*'XVID'), fps, (width, height))

    # Process each frame in the video
    while True:
        ret, frame = cap.read()
        if not ret:
            break
        frame_with_emotion = predict_emotion(frame)
        out.write(frame_with_emotion)

    # Release video capture and writer
    cap.release()
    out.release()

# Define the Gradio interface
demo = gr.Interface(
    fn=process_video,
    inputs=["video", "file"],  # Allow video input from webcam or file
    outputs="video",  # Output video with emotion overlay
    capture_session=True,  # Maintain capture session for video input
    title="Emotion Detection in Video",
    description="Upload a video file or use your webcam to detect emotions in real-time.",
    theme="huggingface",
)

# Launch the Gradio interface
if __name__ == "__main__":
    demo.launch()