Update app.py

app.py

@@ -76,8 +76,8 @@
 #     demo.launch()
     
 ######################################################################################################################################################
-    
 import gradio as gr
+import os
 import cv2
 import numpy as np
 import imutils
@@ -91,6 +91,7 @@ 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)
@@ -112,23 +113,40 @@ def predict_emotion(frame):
                       (238, 164, 64), 2)
     return frame
 
-# Define Gradio interface
-inputs = [
-    gr.inputs.Image(type="numpy", label="Upload Image"),
-    gr.inputs.Video(type="numpy", label="Upload Video")  # Allow for video input
-]
-outputs = [
-    gr.outputs.Video(type="numpy", label="Processed Video"),  # Allow for video output
-    gr.Image()
-]
-examples = [
-    "images/chandler.jpeg",
-    "videos/input_video.mp4"
-]
-
-title = "Emotion Recognition"
-description = "Upload an image or a video, and the model will detect emotions in faces and overlay them on the output."
-
-iface = gr.Interface(fn=predict_emotion, inputs=inputs, outputs=outputs,
-                     examples=examples, title=title, description=description)
-iface.launch()
+# 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()