I am trying to load a model saved as h5 and written in python 3.6, tensorflow 1.4.0 and keras 2.0
However, when loading it up, I get the error with load_model:

ValueError: Could not interpret initializer identifier: {'class_name': 'Orthogonal', 'config': {'gain': 1.0, 'seed': None}}

My code is this:

from tensorflow.keras.models import load_model
from tensorflow.keras.initializers import Initializer, Orthogonal
import tensorflow as tf
from tensorflow import keras


loaded_keras_model = tf.keras.models.load_model(
    "convlstm_ICA_12_train.h5",
)

Can I even use models created in python 3.6 and the old package versions? Or am I troubleshooting wrong?