Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / ericjang/gumbel-softmax issues and pull requests
#13 - recons = tf.reduce_sum(p_x.log_prob(x),1)
Issue -
State: closed - Opened by gitfourteen about 4 years ago
- 1 comment
#12 - why hard sampling should use stop_gradient ？
Issue -
State: open - Opened by kelvinleen almost 5 years ago
#11 - gumbel-softmax in fairseq
Issue -
State: open - Opened by nicolabertoldi over 5 years ago
- 4 comments
#10 - what 'p_x.log_prob(x)' mean?
Issue -
State: open - Opened by WHQ1111 almost 6 years ago
#9 - logits_py incorrect in gumbel_softmax_vae_v2
Issue -
State: open - Opened by backpropper over 6 years ago
- 1 comment
#8 - 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?
Issue -
State: closed - Opened by zhuqunxi over 6 years ago
- 1 comment
#7 - Question regarding KL calculation
Issue -
State: closed - Opened by backpropper over 6 years ago
- 2 comments
#6 - About Unsupervised Clustering Under VAE？
Issue -
State: closed - Opened by LynnHo about 7 years ago
- 1 comment
#5 - Discretization or not in the evaluation ?
Issue -
State: open - Opened by Sunarker about 7 years ago
#4 - error in gs vae v2
Issue -
State: closed - Opened by tigerneil over 7 years ago
- 1 comment
#3 - Code Examples for Semi-Supervised Classification
Issue -
State: open - Opened by lfloeer over 7 years ago
- 3 comments
#2 - Is there empirically good temperature?
Issue -
State: closed - Opened by wsjeon about 8 years ago
- 2 comments
#1 - Should `y` be sparse/binary?
Issue -
State: closed - Opened by bkj about 8 years ago
- 1 comment