[BUG]: Bug ao tentar carregar modelo pré-treinado

[Dev-RodriguesRenan]

Estou tendo problemas ao tentar carregar o modelo pré-treinado pelo Teachble Machine, aparece a seguinte mensagem

Error when deserializing class 'DepthwiseConv2D' using config={'name': 'expanded_conv_depthwise', 'trainable': True, 'dtype': 'float32', 'kernel_size': [3, 3], 'strides': [1, 1], 'padding': 'same', 'data_format': 'channels_last', 'dilation_rate': [1, 1], 'groups': 1, 'activation': 'linear', 'use_bias': False, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'bias_regularizer': None, 'activity_regularizer': None, 'bias_constraint': None, 'depth_multiplier': 1, 'depthwise_initializer': {'class_name': 'VarianceScaling', 'config': {'scale': 1, 'mode': 'fan_avg', 'distribution': 'uniform', 'seed': None}}, 'depthwise_regularizer': None, 'depthwise_constraint': None}.

utilizei o mesmo código fornecido pela plataforma do Teachlab Machine, mas mesmo assim não consigo carregar o modelo keras_model.h5

from tensorflow.keras.models import load_model  # TensorFlow is required for Keras to work
from PIL import Image, ImageOps  # Install pillow instead of PIL
import numpy as np

def carregar_modelo(path_to_model,path_to_text_class):
  # Disable scientific notation for clarity
  np.set_printoptions(suppress=True)
  # Load the model
  model = load_model(path_to_model, compile=False)

  # Load the labels
  class_names = open(path_to_text_class, "r").readlines()
  return model,class_names


def processing_and_classifier(image_path,model,class_names):
  # Create the array of the right shape to feed into the keras model
  # The 'length' or number of images you can put into the array is
  # determined by the first position in the shape tuple, in this case 1
  data = np.ndarray(shape=(1, 224, 224, 3), dtype=np.float32)
  # Replace this with the path to your image
  image = Image.open(image_path).convert("RGB")

  # resizing the image to be at least 224x224 and then cropping from the center
  size = (224, 224)
  image = ImageOps.fit(image, size, Image.Resampling.LANCZOS)

  # turn the image into a numpy array
  image_array = np.asarray(image)

  # Normalize the image
  normalized_image_array = (image_array.astype(np.float32) / 127.5) - 1

  # Load the image into the array
  data[0] = normalized_image_array

  # Predicts the model
  prediction = model.predict(data)
  index = np.argmax(prediction)
  class_name = class_names[index]
  confidence_score = prediction[0][index]

  # Print prediction and confidence score
  print("Class:", class_name[2:], end="")
  print("Confidence Score:", confidence_score)
  return class_name[2:],confidence_score

Por favor se puderem me auxiliar a resolver esse erro nas novas versões do tensorflow e keras, pois consegui resolver com versões inferiores como 2.13.0 do tensorflow, porém há um bug que só tem como instalar essa versão do tensorflow caso esteja em um jupyter notebook, caso contrário o pip não o encontra a versão

ERROR: Could not find a version that satisfies the requirement tensorflow==2.13.0 (from versions: 2.16.0rc0, 2.16.1, 2.16.2, 2.17.0rc0, 2.17.0rc1, 2.17.0, 2.18.0rc0, 2.18.0rc1)
ERROR: No matching distribution found for tensorflow==2.13.0