Hi Ruishu,
Thanks for your post and the code. I had a question in gmvae.py. I was wondering why you initialize y as y = tf.add(y_, Constant(np.eye(10)[i], name='hot_at_{:d}'.format(i))) and use this y in z[i], zm[i], zv[i] = qz_graph(xb, y), instead of using the recognized qy qy_logit, qy = qy_graph(xb)? Any rationale behind it?
Hi Ruishu,
Thanks for your post and the code. I had a question in gmvae.py. I was wondering why you initialize y as
y = tf.add(y_, Constant(np.eye(10)[i], name='hot_at_{:d}'.format(i)))and use this y inz[i], zm[i], zv[i] = qz_graph(xb, y), instead of using the recognized qyqy_logit, qy = qy_graph(xb)? Any rationale behind it?