Update app.py

app.py

@@ -8,66 +8,66 @@ 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 = 'model_2_aug_nocall_BEST/model_2_aug_nocall_entire_model.h5'
+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']
 
-# Function to predict emotions from a frame
-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()]
-        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)}
 
-# Define input and output components for Gradio
+# face_detector_mtcnn = MTCNN()
+classifier = load_model(emotion_model_path)
 
-image_input = [
-        gr.components.Image(sources="webcam", label="Your face"),
-        gr.components.File(label="Upload Image or Video")
-      ]
-output = [
-        gr.components.Image(label="Predicted Emotion"),
-        gr.components.Label(num_top_classes=2, label="Top 2 Probabilities")
-      ]
+def predict_emotion(image):
 
-# Launch the Gradio interface
-title = "Facial Emotion Recognition"
-description = "How well can this model predict your emotions? Take a picture with your webcam, or upload an image, and it will guess if you are happy, sad, angry, disgusted, scared, surprised, or neutral."
-thumbnail = "https://raw.githubusercontent.com/gradio-app/hub-emotion-recognition/master/thumbnail.png"
+    faces = face_detection(image)
 
-example_images = [
-    [
-        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")
-    ]
-]
+    for face in faces:
+        x,y,w,h = face['box']
+
+        roi = image[y:y+h,x:x+w]
+        
+        # Converting the region of interest to grayscale, and resize
+        roi_gray = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
+        roi_gray = cv2.resize(roi_gray,(48,48),interpolation=cv2.INTER_AREA)
+
+        img = roi_gray.astype('float')/255.0
+        img = img_to_array(img)
+        img = np.expand_dims(img,axis=0)
+
+        prediction = classifier.predict(img)[0]
+        #top_indices = np.argsort(prediction)[-2:]
+        #top_emotion = top_indices[1]
+        #second_emotion = top_indices[0]
+        #label = emotions[top_emotion]
+        confidences = {emotions[i]: float(prediction[i]) for i in range(len(emotions))}
+
+    return confidences
+
+
+
+demo = gr.Interface(
+    fn = predict_emotion,
+    inputs = gr.Image(type="numpy"),
+    outputs = gr.Label(num_top_classes=9),
+    #flagging_options=["blurry", "incorrect", "other"],
+    examples = [
+        os.path.join(os.path.dirname(__file__), "images/Image_1.jpg"),
+        os.path.join(os.path.dirname(__file__), "images/Image_2.jpg"),
+        os.path.join(os.path.dirname(__file__), "images/Image_3.jpg"),
+        os.path.join(os.path.dirname(__file__), "images/Image_4.jpg"),
+        os.path.join(os.path.dirname(__file__), "images/Image_5.jpg"),
+        os.path.join(os.path.dirname(__file__), "images/Image_6.jpg"),
+        os.path.join(os.path.dirname(__file__), "images/Image_7.jpg"),
+        os.path.join(os.path.dirname(__file__), "images/Image_8.jpg"),
+        os.path.join(os.path.dirname(__file__), "images/Image_9.jpg"),
+        os.path.join(os.path.dirname(__file__), "images/Image_10.jpg"),
+     
+    ],
+    title = "Whatchu feeling?",
+    theme = "shivi/calm_seafoam"
+)
     
-gr.Interface(fn=predict, inputs=image_input, outputs=output, examples=example_images,
-            title=title, description=description, thumbnail=thumbnail).launch()
+
+
+if __name__ == "__main__":
+    demo.launch()