Update app.py

app.py

@@ -21,42 +21,34 @@ emotion_classifier = load_model(emotion_model_path, compile=False)
 EMOTIONS = ['neutral','happiness','surprise','sadness','anger','disgust','fear','contempt','unknown']
 
 
-def predict(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)
-
-    frameClone = frame.copy()
-    if len(faces) > 0:
-        faces = sorted(faces, reverse=True,
-                       key=lambda x: (x[2] - x[0]) * (x[3] - x[1]))[0]
-        (fX, fY, fW, fH) = 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
+def predict(frame_or_path):
+    if isinstance(frame_or_path, np.ndarray):  # If input is a webcam frame
+        frame = imutils.resize(frame_or_path, width=300)
+    else:  # If input is a file path
+        frame = cv2.imread(frame_or_path)
+        if frame is None:
+            return None, "Error: Unable to read image or video."
+        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)
+        if len(faces) == 0:
+            return frame, "No face detected."
+        (fX, fY, fW, fH) = faces[0]
         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()]
-    else:
-        return frameClone, "Can't find your face"
-
-    probs = {}
-    cv2.putText(frameClone, label, (fX, fY - 10),
-                cv2.FONT_HERSHEY_DUPLEX, 1, (238, 164, 64), 1)
-    cv2.rectangle(frameClone, (fX, fY), (fX + fW, fY + fH),
-                  (238, 164, 64), 2)
+        cv2.putText(frame, label, (fX, fY - 10),
+                    cv2.FONT_HERSHEY_DUPLEX, 1, (238, 164, 64), 1)
+        cv2.rectangle(frame, (fX, fY), (fX + fW, fY + fH),
+                      (238, 164, 64), 2)
+        return frame, {emotion: float(prob) for emotion, prob in zip(EMOTIONS, preds)}
 
-    for (i, (emotion, prob)) in enumerate(zip(EMOTIONS, preds)):
-        probs[emotion] = float(prob)
 
-    return frameClone, probs
 
 # Define Gradio input and output components
 image_input = gr.components.Image(type='numpy', label="Upload Image or Video")