I got different output shape with different Deep Learning model declaration

Question

I am new in this field, and still tinkering with other's codes to see how they work. This code is from https://github.com/mwitiderrick/stockprice I tried to declare the model in another format as follow

model = Sequential([
        LSTM(units = 50, return_sequences=True,input_shape = (X_train.shape[1],1)), 
        Dropout(0.2),
        LSTM(units =50,return_sequences=True), 
        Dropout(0.2),
        LSTM(units =50,return_sequences=True), 
        Dropout(0.2),
        LSTM(units =50,return_sequences=True), 
        Dropout(0.2),
        Dense(units=1)
])

model.compile(optimizer = 'adam', loss = 'mean_squared_error')

model.fit(X_train, y_train, epochs=1, batch_size = 32)

Then use this code to predict the output

predicted_stock_price = model.predict(X_test)

However, the predicted_stock_price.shape show (16, 60, 1) meanwhile the original code with this format

# Initialising the RNN
regressor = Sequential()

# Adding the first LSTM layer and some Dropout regularisation
regressor.add(LSTM(units = 50, return_sequences = True, input_shape = (X_train.shape[1], 1)))
regressor.add(Dropout(0.2))

# Adding a second LSTM layer and some Dropout regularisation
regressor.add(LSTM(units = 50, return_sequences = True))
regressor.add(Dropout(0.2))

# Adding a third LSTM layer and some Dropout regularisation
regressor.add(LSTM(units = 50, return_sequences = True))
regressor.add(Dropout(0.2))

# Adding a fourth LSTM layer and some Dropout regularisation
regressor.add(LSTM(units = 50))
regressor.add(Dropout(0.2))

# Adding the output layer
regressor.add(Dense(units = 1))

# Compiling the RNN
regressor.compile(optimizer = 'adam', loss = 'mean_squared_error')

# Fitting the RNN to the Training set
regressor.fit(X_train, y_train, epochs = 1, batch_size = 32)

show (16,1) shape

What could have caused this? The other lines are the same, Thanks in advance

Answer 1

Remove return_sequences=True from the fourth LSTM layer