z_est_bn = (z_est[l] - m) / v

rinuboney / ladder

Ladder network is a deep learning algorithm that combines supervised and unsupervised learning.

MIT License

242 stars 92 forks source link

z_est_bn = (z_est[l] - m) / v #22

Open daniadag opened 4 years ago

daniadag commented 4 years ago

why we need to put this line in decoder in line 179??? after you apply batch normalization

it seems like you apply mean and v for output layer before and after g_gauss u = batch_normalization(u) z_est[l] = g_gauss(z_c, u, layer_sizes[l]) z_est_bn = (z_est[l] - m) / v