So I am trying out an open-source model to get my camera to detect the emotion of my face. This is the code I tried:

import numpy as np
import cv2
from keras.preprocessing import image

#opencv initialization

face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

cap = cv2.VideoCapture(0)

#face expression recognizer initialization
from keras.models import model_from_json
from tensorflow.keras.models import Sequential, Model
model = model_from_json(open("facial_expression_model_structure.json", "r").read())
model.load_weights('facial_expression_model_weights.h5') #load weights

emotions = ('angry', 'disgust', 'fear', 'happy', 'sad', 'surprise', 'neutral')

while(True):
    ret, img = cap.read()
    #img = cv2.imread('C:/Users/IS96273/Desktop/hababam.jpg')
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

    faces = face_cascade.detectMultiScale(gray, 1.3, 5)

    print(faces) #locations of detected faces

    for (x,y,w,h) in faces:
        cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2) #draw rectangle to main image
        
        roi_gray = gray[y:y+h, x:x+w] 
        roi_color = img[y:y+h, x:x+w]

        detected_face = img[int(y):int(y+h), int(x):int(x+w)] #crop detected face
        detected_face = cv2.cvtColor(detected_face, cv2.COLOR_BGR2GRAY) #transform to gray scale
        detected_face = cv2.resize(detected_face, (48, 48)) #resize to 48x48

        img_pixels = image.img_to_array(detected_face)
        img_pixels = np.expand_dims(img_pixels, axis = 0)

        img_pixels /= 255 #pixels are in scale of [0, 255]. normalize all pixels in scale of [0, 1]

        predictions = model.predict(img_pixels) #store probabilities of 7 expressions

        #find max indexed array 0: angry, 1:disgust, 2:fear, 3:happy, 4:sad, 5:surprise, 6:neutral
        max_index = np.argmax(predictions[0])

        emotion = emotions[max_index]

        #write emotion text above rectangle
        cv2.putText(img, emotion, (int(x), int(y)), cv2.FONT_HERSHEY_PLAIN, 1, (255,255,255), 2)

        #process on detected face end

    cv2.imshow('img',img)

    if cv2.waitKey(1) & 0xFF == ord('q'): #press q to quit
        break

#kill open cv things
cap.release()
cv2.destroyAllWindows()

So this code actually works fine on Jupyter Notebook but once I copied and pasted it to VSCode there is the following error regarding the line 18 where model = model_from_json(open("facial_expression_model_structure.json", "r").read()):

Traceback (most recent call last):
  File "c:...<directory where the Python file is>...DeepFace2.py", line 19, in <module>
    model = model_from_json(open("facial_expression_model_structure.json", "r").read())
  File "C:<my username>.virtualenvsmp_sort-dE8CVHaGlibsite-packageskerassrcmodelsmodel.py", line 583, in model_from_json
    return serialization_lib.deserialize_keras_object(
  File "C:<my username>.virtualenvsmp_sort-dE8CVHaGlibsite-packageskerassrcsavingserialization_lib.py", line 694, in deserialize_keras_object
    cls = _retrieve_class_or_fn(
  File "C:<my username>.virtualenvsmp_sort-dE8CVHaGlibsite-packageskerassrcsavingserialization_lib.py", line 812, in _retrieve_class_or_fn
    raise TypeError(
TypeError: Could not locate class 'Sequential'. Make sure custom classes are decorated with `@keras.saving.register_keras_serializable()`. Full object config: {'class_name': 'Sequential', 'backend': 'tensorflow', 'config': [{'class_name': 'Conv2D', 'config': {'dtype': 'float32', 'padding': 'valid', 'filters': 64, 'trainable': True, 'activation': 'relu', 'bias_constraint': None, 'strides': [1, 1], 'name': 'conv2d_1', 'dilation_rate': [1, 1], 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'distribution': 'uniform', 'mode': 'fan_avg', 'scale': 1.0, 'seed': None}}, 'bias_regularizer': None, 'kernel_constraint': None, 'kernel_regularizer': None, 'data_format': 'channels_last', 'use_bias': True, 'batch_input_shape': [None, 48, 48, 1], 'activity_regularizer': None, 'kernel_size': [5, 5], 'bias_initializer': {'class_name': 'Zeros', 'config': {}}}}, {'class_name': 'MaxPooling2D', 'config': {'name': 'max_pooling2d_1', 'padding': 'valid', 'pool_size': [5, 5], 'data_format': 'channels_last', 'trainable': True, 'strides': [2, 2]}}, {'class_name': 'Conv2D', 'config': {'padding': 'valid', 'filters': 64, 'trainable': True, 'activation': 'relu', 'bias_constraint': None, 'strides': [1, 1], 'name': 'conv2d_2', 'dilation_rate': [1, 1], 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'distribution': 'uniform', 'mode': 'fan_avg', 'scale': 1.0, 'seed': None}}, 'bias_regularizer': None, 'kernel_constraint': None, 'kernel_regularizer': None, 'data_format': 'channels_last', 'use_bias': True, 'activity_regularizer': None, 'kernel_size': [3, 3], 'bias_initializer': {'class_name': 'Zeros', 'config': {}}}}, {'class_name': 'Conv2D', 'config': {'padding': 'valid', 'filters': 64, 'trainable': True, 'activation': 'relu', 'bias_constraint': None, 'strides': [1, 1], 'name': 'conv2d_3', 'dilation_rate': [1, 1], 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'distribution': 'uniform', 'mode': 'fan_avg', 'scale': 1.0, 'seed': None}}, 'bias_regularizer': None, 'kernel_constraint': None, 'kernel_regularizer': None, 'data_format': 'channels_last', 'use_bias': True, 'activity_regularizer': None, 'kernel_size': [3, 3], 'bias_initializer': {'class_name': 'Zeros', 'config': {}}}}, {'class_name': 'AveragePooling2D', 'config': {'name': 'average_pooling2d_1', 'padding': 'valid', 'pool_size': [3, 3], 'data_format': 'channels_last', 'trainable': True, 'strides': [2, 2]}}, {'class_name': 'Conv2D', 'config': {'padding': 'valid', 'filters': 128, 'trainable': True, 'activation': 'relu', 'bias_constraint': None, 'strides': [1, 1], 'name': 'conv2d_4', 'dilation_rate': [1, 1], 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'distribution': 'uniform', 'mode': 'fan_avg', 'scale': 1.0, 'seed': None}}, 'bias_regularizer': None, 'kernel_constraint': None, 'kernel_regularizer': None, 'data_format': 'channels_last', 'use_bias': True, 'activity_regularizer': None, 'kernel_size': [3, 3], 'bias_initializer': {'class_name': 'Zeros', 'config': {}}}}, {'class_name': 'Conv2D', 'config': {'padding': 'valid', 'filters': 128, 'trainable': True, 'activation': 'relu', 'bias_constraint': None, 'strides': [1, 1], 'name': 'conv2d_5', 'dilation_rate': [1, 1], 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'distribution': 'uniform', 'mode': 'fan_avg', 'scale': 1.0, 'seed': None}}, 'bias_regularizer': None, 'kernel_constraint': None, 'kernel_regularizer': None, 'data_format': 'channels_last', 'use_bias': True, 'activity_regularizer': None, 'kernel_size': [3, 3], 'bias_initializer': {'class_name': 'Zeros', 'config': {}}}}, {'class_name': 'AveragePooling2D', 'config': {'name': 'average_pooling2d_2', 'padding': 'valid', 'pool_size': [3, 3], 'data_format': 'channels_last', 'trainable': True, 'strides': [2, 2]}}, {'class_name': 'Flatten', 'config': {'name': 'flatten_1', 'trainable': True}}, {'class_name': 'Dense', 'config': {'use_bias': True, 'trainable': True, 'activation': 'relu', 'activity_regularizer': None, 'name': 'dense_1', 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'distribution': 'uniform', 'mode': 'fan_avg', 'scale': 1.0, 'seed': None}}, 'bias_regularizer': None, 'kernel_regularizer': None, 'units': 1024, 'bias_constraint': None, 'kernel_constraint': None, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}}}, {'class_name': 'Dropout', 'config': {'name': 'dropout_1', 'trainable': True, 'rate': 0.2}}, {'class_name': 'Dense', 'config': {'use_bias': True, 'trainable': True, 'activation': 'relu', 'activity_regularizer': None, 'name': 'dense_2', 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'distribution': 'uniform', 'mode': 'fan_avg', 'scale': 1.0, 'seed': None}}, 'bias_regularizer': None, 'kernel_regularizer': None, 'units': 1024, 'bias_constraint': None, 'kernel_constraint': None, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}}}, {'class_name': 'Dropout', 'config': {'name': 'dropout_2', 'trainable': True, 'rate': 0.2}}, {'class_name': 'Dense', 'config': {'use_bias': True, 'trainable': True, 'activation': 'softmax', 'activity_regularizer': None, 'name': 'dense_3', 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'distribution': 'uniform', 'mode': 'fan_avg', 'scale': 1.0, 'seed': None}}, 'bias_regularizer': None, 'kernel_regularizer': None, 'units': 7, 'bias_constraint': None, 'kernel_constraint': None, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}}}], 'keras_version': '2.0.8'}

I checked on VSCode and it shows that my keras version is 3.5.0 and my tensorflow version is 2.17.0 on VSCode which seems to be the latest version. So what seems to be the problem on VSCode?

Edit: Added the full traceback as someone in the comments asked for it.