Demo example for credit card has train_data shape: (284807,29)
If I am not mistaken, 29 is the timestep here (and not the number of the values in the observation)?
I have my data in shape (samples, timesteps, values) can I still use keras anomaly detection?
Demo example for credit card has train_data shape: (284807,29) If I am not mistaken, 29 is the timestep here (and not the number of the values in the observation)?
I have my data in shape (samples, timesteps, values) can I still use keras anomaly detection?