Comments (3)
That's odd. I've never encountered this issue.
When I originally run the experiments, I used Theano v0.9.0.
I tried to reproduce the error with Theano v0.9.0 and Theano v1.0.2 (latest version), but I couldn't. The code seems to run fine as is.
My understanding is that you're issuing
python run_experiments.py mnist
and then the error happens when Conditional MAF is to be trained. When a model is being trained, the code displays training info on screen, something like:
Epoch = 1, train loss = 839.124948406, validation loss = 1755.41093458
Epoch = 2, train loss = 709.554258655, validation loss = 1751.73216701
...
Can you provide more details on when exactly you encounter the error? What does the code output up to the point the error happens? Are the other models (MADE, MADE MoG, RealNVP, and their conditional versions) trained successfully?
from maf.
@tdeboissiere Sorry to use this discuss on another question.
I want to train a mafs.ConditionalMaskedAutoregressiveFlow, but the model loss always go to negative.
It starts at like 58.7, but after few steps(about 800) it goes negative.
something like: Epoch 3 - Step 221102 - loss -426.319 - lr 1.67e-05 - 0.32 s/step
Does this normal for maf loss go to negative? because the determine Jacoian term?
If this is not normal, any suggestions I can debug this? lack or too much of params to learn? need more regularization?
I am using tensorflow code which adapt Theano to Tensorflow: https://github.com/spinaotey/maf_tf
from maf.
This is totally normal. Log-likelihood loss doesn't have to be positive, its lowest value can be negative.
from maf.
Related Issues (12)
- Log-likelihood of Gaussian MADE HOT 2
- Can you provide the preprocessed datasets? HOT 1
- Link to the datasets in the README is dead HOT 4
- Error in log likelihood computation HOT 7
- Batch normalization HOT 1
- How you preprocess your data? HOT 2
- Problem with preprocessing of UCI datasets, especially MiniBooNE HOT 1
- Updation requested HOT 2
- Preprocessed data HOT 2
- Migration to version python3.6.4 HOT 1
- Broken datasets due to pandas API changes 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 maf.