change the size of training data

[ErisGe]

I saw that your answer about training data'size, and said that 'by setting the length of the first axis to a smaller number'. But how can I change this value?

def load_data_from_npz(filename): """Load and return the training data from a npz file (sparse format).""" with np.load(filename) as f: data = np.zeros(f['shape'], np.bool_) data[[x for x in f['nonzero']]] = True return data

[salu133445]

Hi, you can replace the last line with return data[:5000] for example.

[ErisGe]

Oh, thank you so much!