Closed GrahamboJangles closed 4 years ago
Also, in this line, why is the data flipped? Doesn't this mean that it will predict the prices in the reverse order?
Data needs to be flipped if it is in ascending order. When you are building the candle graphs with graphwerk.py
you have to start with the data that is older. For example if the data is starting from day 1 and goes to day 5 then you don't need to flip the data. If its other way around then you need to flip it.
You have to load saved model and weights using
from keras.models import load_model
model = load_model('my_model.h5')
Method to be able to load it before going on with more training.
Is there a way to load a model to continue training? I tried throwing in
load_model()
right before training starts but it doesn't seem to work.