Problem of the result On Deep Learning-Based Channel Decoding.ipynb

[tom12345a]

Hi. I am new in deep learning. As I tried to process the result by following the code exactly, the NN line is missing in the result. Even I increase the num_words to 1000000 or SNR_points to become bigger, The NN line is still missing.

All the code is same to you but the only difference is that I changed std=sigma to stddev=sigma.
Also, I changed return K.sum(K.not_equal(y_true, K.round(y_pred))) to
return tf.reduce_mean(K.cast(K.equal(y_true, K.round(y_pred)),dtype = 'int32')) as there is some error when running the code.

[hnuliuxin]

I think change return K.sum(K.not_equal(y_true, K.round(y_pred))) to
return tf.reduce_mean(K.cast(K.equal(y_true, K.round(y_pred)),dtype = 'int32')) may be the problem.