Teaching a Variational Autoencoder (VAE) to draw MNIST characters
Felix Mohr

Nicely written, thanks! One quick question - why is the inputs_decoder = 49 * dec_in_channels/2 ? This causes error in the decoder: x = tf.layers.dense(sampled_z, units= inputs_decoder, activation=lrelu)

as the units is not an integer.


One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.