np.floor(data.astype('float32') / 128)
Hello, the original shape of data is (28,28,1) and the data elements are 0/1,
so I wonder why we need to `/128`.--- [Visit Topic](https://discuss.mxnet.io/t/naive-bayes/5155/2) or reply to this email to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.mxnet.io/email/unsubscribe/ad218152086beee0e1f2bf3162eb231905ff0fd06f7ae3748f65643392416938).
