Comments (4)
Thanks for this! I believe I have just fixed it in latest version 1.7.10. Basically I switched the models to run double precision by default when using the DeepWrapper class (this helps with some stability issues e.g. #39). As you have noticed this wasn't compatible with the MNIST datasets which gave floats.
- I have now changed DeepWrapper to put things in double before passing to the model.
- Have also added a test that runs a subset of the tutorial to check it runs
Your comment also raised a different issue which was that the reconstruction loss in the autoencoder was reduce='sum' which is bigger with larger batch size so needs more tuning of learning rate.
- Have changed this to reduce='mean' which produces much more sensible losses and convergence for DCCAE and SplitAE
from cca_zoo.
I have uploaded a new run of the tutorial which seems to run OK so tentatively closing this but let me know if further issues
from cca_zoo.
Note - when running the notebook again you may need to run:
!pip install cca-zoo[deep,probabilistic] --upgrade
To get the new version :)
from cca_zoo.
Thank you @jameschapman19 ! That was fast! It is all working great now.
Also thank you for the AE 'reduce' parameter fix, it definitely achieves much more reasonable losses.
from cca_zoo.
Related Issues (20)
- Pass down parameters to BaseSearchCV in cca_zoo.model_selection.GridSearchCV
- the value of the model.fit_transform() is nan HOT 7
- Could you provide a 3-group CCA method? HOT 2
- What happened to the scale argument? HOT 19
- Cannot simulate data HOT 2
- TerminatedWorkerError when using GridSearchCV HOT 29
- Do you have a CCA method incorporated with Multivariate Granger causality? HOT 3
- cca_zoo.model_selection.GridSearchCV's param_grid parameter should accept any type of iterator HOT 3
- Implement CCA-classes that can account for sample groups HOT 2
- predict() method for models? HOT 6
- SPLS is slower than it used to be.
- Installation error HOT 14
- The algorithm failed to converge because the input matrix is ill-conditioned or has too many repeated eigenvalues (error code: 1). HOT 2
- Is the loss function calculated on the raw data? HOT 22
- Is averaged pairwise correlation the first principle to construct MCCA indices? HOT 6
- Unnecessary overhead when calculating CCALoss HOT 5
- SCCA_PMD Inner Loop Convergence Warning in cca_zoo
- SVD Not Converging HOT 2
- torch._C._LinAlgError: torch.linalg.solve: The solver failed because the input matrix is singular. HOT 6
- Inverse transforms
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 cca_zoo.