Comments (2)
from zhusuan.
Hi @ssydasheng ,
Actually that's what I intended to. In the new api, there is no further assumptions about shape of the Tensors. no (batch_size, n_samples)
anymore. With new StochasticTensor
s, you can sample in any sample_dim
you want. You can take a look at examples/vae.py. Over the days I have thought about for a graphical model, there is nothing special to batch_size
, it's just a plate (a rectangle). So my choice in vae.py is just build the model (p(x,z)) like the graphical view (z_mean
as (n_z,)
, z_logstd
as (n_z,)
, z
as (batch_size, n_z)
), what I add to make it more suitable in variational setting is just adding a n_particles
(i.e. n_samples) dimension before all of these shapes, which can be seen as we allow multiple samples (particles) to pass through a node in the graphical model. That meets the need when getting q(z) samples of shape (n_particles, batch_size, n_z)
so that these samples can be passed into models.
Normal and Bernoulli actually means independent Normal and independent Bernoulli. Discrete will sum over the last dimension. If you look at my new vae under examples/, it sums logpdf by hand over the dimension you want and then gets passed to advi. I will further change the api of advi to make this more comfortable.
For your case, if w is of shape (n1, n2)
, I guess you can define w_mean, w_logstd, w
as shape (n_particles, n1, n2)
, qw_mean, qw_logstd
can be as shape (n1, n2)
, and qw=Normal(qw_mean, qw_logstd, sample_dim=0, n_samples=n_particles)
Above may be a little messy to understand, we can chat in details.
from zhusuan.
Related Issues (20)
- Posterior and parameters analysis HOT 1
- questions about dlgm_nf.py HOT 1
- Can't compute prior (local_log_prob) of a StochasticTensor inside tf.scan (in LSTM cell) HOT 11
- Clarifying the * N in log_joint? HOT 4
- Dirichlet + Categorical or Dirichlet + Multinomial toy example ? HOT 5
- Collaboration with TensorLayer HOT 5
- save and restore models? HOT 4
- I have some trouble translating a model from PyMC3 HOT 4
- 请问哪里能找到zhusuan的中文文档? HOT 4
- AttributeError: module 'progressbar' has no attribute 'DataSize' HOT 1
- Why the std of y_mean is so small? HOT 7
- Memory leaks caused by VariationalObjective HOT 2
- How to use custom Hamiltonian? HOT 5
- Eager executation HOT 2
- Get logp from SGMCMC HOT 2
- module 'tensorflow' has no attribute 'make_template' HOT 1
- The examples of ‘semi_supervised_vae’ cannot run successfully HOT 1
- cant install ZhuSuan HOT 4
- AttributeError: module 'tensorflow' has no attribute 'log'
- Examples code is out dated and doesn't work with Tensorflow 2.x HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from zhusuan.