ericjang gumbel-softmax issues - Githubissues

ericjang / gumbel-softmax

categorical variational autoencoder using the Gumbel-Softmax estimator

MIT License

425 stars 101 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

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

#13 gitfourteen closed 3 years ago
1
why hard sampling should use stop_gradient ？

#12 kelvinleen opened 4 years ago
0
gumbel-softmax in fairseq

#11 nicolabertoldi opened 4 years ago
4
what 'p_x.log_prob(x)' mean?

#10 WHQ1111 opened 5 years ago
0
logits_py incorrect in gumbel_softmax_vae_v2

#9 backpropper opened 6 years ago
1
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 zhuqunxi closed 6 years ago
1
Question regarding KL calculation

#7 backpropper closed 6 years ago
2
About Unsupervised Clustering Under VAE？

#6 LynnHo closed 4 years ago
1
Discretization or not in the evaluation ?

#5 Sunarker opened 6 years ago
0
error in gs vae v2

#4 tigerneil closed 7 years ago
1
Code Examples for Semi-Supervised Classification

#3 lfloeer opened 7 years ago
3
Is there empirically good temperature?

#2 wsjeon closed 7 years ago
2
Should `y` be sparse/binary?

#1 bkj closed 7 years ago
1