ericjang/gumbel-softmax

Issues

• Code Examples for Semi-Supervised Classification

  #3 opened 8 years ago by lfloeer
  3

• recons = tf.reduce_sum(p_x.log_prob(x),1)

  #13 opened 4 years ago by gitfourteen
  1

• About Unsupervised Clustering Under VAE？

  #6 opened 4 years ago by LynnHo
  1

• why hard sampling should use stop_gradient ？

  #12 opened 5 years ago by kelvinleen
  0

• gumbel-softmax in fairseq

  #11 opened 5 years ago by nicolabertoldi
  4

• logits_py incorrect in gumbel_softmax_vae_v2

  #9 opened 7 years ago by backpropper
  1

• what 'p_x.log_prob(x)' mean?

  #10 opened 6 years ago by WHQ1111
  0

• Question regarding KL calculation

  #7 opened 7 years ago by backpropper
  2

• Great thanks for your code. I have a question. If I have a matrix, whose elements is discrete (i.e., binary state 0 or 1), needed to be trained under a given loss function, how should I train it?

  #8 opened 7 years ago by zhuqunxi
  1

• Discretization or not in the evaluation ?

  #5 opened 7 years ago by Sunarker
  0

• error in gs vae v2

  #4 opened 8 years ago by tigerneil
  1

• Is there empirically good temperature?

  #2 opened 8 years ago by wsjeon
  2

• Should `y` be sparse/binary?

  #1 opened 8 years ago by bkj
  1