Kernel Shutdown While model.predict() Keras Model - tensorflow

Question

so I'm currently having an issue that every time I predict my loaded model, my Jupyter Notebook's kernel shut down.
So I was given this Keras model that has this model summary:
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_1 (Dense) (None, 100) 200
_________________________________________________________________
re_lu_1 (ReLU) (None, 100) 0
_________________________________________________________________
dropout_1 (Dropout) (None, 100) 0
_________________________________________________________________
dense_2 (Dense) (None, 50) 5050
_________________________________________________________________
re_lu_2 (ReLU) (None, 50) 0
_________________________________________________________________
dropout_2 (Dropout) (None, 50) 0
_________________________________________________________________
dense_3 (Dense) (None, 1) 51
=================================================================
Total params: 5,301
Trainable params: 5,301
Non-trainable params: 0
I was planning to save this model using this method that I got online. I saved the entire model. Then, I tried to load the saved model onto a different notebook. Done dimension/shape adjustment and I started noticing that every time I did model.predict(), my kernel shuts and gave no error massages. So I started to do this backwards, which is trying to predict on the original notebook, where the model was trained. And I found no error. My hypothesis is:
There's nothing wrong with the model. Because this it can predict one data. Anything greater than that, it'll crush.
The problem came from saving and loading the model
This is my code for saving and loading my model
MODEL ORIGIN NOTEBOOK
Has anyone ever encountered the same problem? The below code is my code:
#Model architecture
#Model ANN
model = Sequential()
model.add(Dense(100, input_shape=(1,)))
model.add(ReLU())
model.add(Dropout(.5))
model.add(Dense(50))
model.add(ReLU())
model.add(Dropout(.5))
model.add(Dense(1))
model.compile(optimizer='rmsprop', loss='mse', metrics=['mae'])
model.fit(X_train, y_train, epochs=1000, batch_size=100, validation_data=(X_valid, y_valid))
# ATTEMPT 1 save the model to disk
filename = 'model_pake_pickle_bener.sav'
pickle.dump(model, open(filename, 'wb'))
DIFFERENT NOTEBOOK
This is where things gone wrong
#Load the saved model
filename = 'model_pake_pickle_bener.sav'
loaded_model = pickle.load(open(filename, 'rb'))
#reduce number of data used
bersih = bessp[:2]
#Introducing our dataset to tf (Voltage only)
X = bersih['Voltage_y'].values
y = bersih['SOC'].values
#Reshaping
X = X.reshape(X.shape[0], 1)
y = y.reshape(y.shape[0], 1)
#Adjustment
X = np.asarray(X).astype('float32')
y = loaded_model.predict(X)
I've tried using h5 file and it ended up the same as the others.

Answer 1

Have you tried saving and loading the model with the direct object methods? I noticed that you use pickle, but it's recommended to use (taken from the documentation):
model = ... # Get model (Sequential, Functional Model, or Model subclass)
model.save('path/to/location')
To load the model in your second notebook:
from tensorflow import keras
model = keras.models.load_model('path/to/location')