-
Notifications
You must be signed in to change notification settings - Fork 4
Comparing changes
Open a pull request
base repository: IntelLabs/bayesian-torch
base: v0.1
head repository: IntelLabs/bayesian-torch
compare: v0.2.0
- 16 commits
- 14 files changed
- 2 contributors
Commits on Dec 8, 2021
-
updates to support dnn to bnn imodel auto conversion
msubedar committedDec 8, 2021 Configuration menu - View commit details
-
Copy full SHA for 90bf260 - Browse repository at this point
Copy the full SHA 90bf260View commit details -
updates to support dnn to bnn imodel auto conversion
msubedar committedDec 8, 2021 Configuration menu - View commit details
-
Copy full SHA for b98ff19 - Browse repository at this point
Copy the full SHA b98ff19View commit details
Commits on Dec 16, 2021
-
Merge pull request #11 from msubedar/dnn2bnn
Adding new feature to create Bayesian deep neural network model from predefined deterministic model architecture i.e. drop-in replacements of Convolutional, Linear and LSTM layers to corresponding Bayesian layers (configured by 'const_bnn_prior_parameters' to set the prior parameters and sampling estimator - Reparameterization or Flipout method). This PR will enable seamless conversion of existing topology of larger models to Bayesian models for extending towards uncertainty-aware applications.
Configuration menu - View commit details
-
Copy full SHA for 8fe84f9 - Browse repository at this point
Copy the full SHA 8fe84f9View commit details -
Configuration menu - View commit details
-
Copy full SHA for 99edabc - Browse repository at this point
Copy the full SHA 99edabcView commit details -
Configuration menu - View commit details
-
Copy full SHA for 81d7e89 - Browse repository at this point
Copy the full SHA 81d7e89View commit details -
update the posterior variational param init value
Signed-off-by: Ranganath Krishnan <ranganath.krishnan@intel.com>
Configuration menu - View commit details
-
Copy full SHA for da68be8 - Browse repository at this point
Copy the full SHA da68be8View commit details -
remove duplicate kl_loss definition in Conv1dReparameterization layer
Signed-off-by: Ranganath Krishnan <ranganath.krishnan@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 1e85c50 - Browse repository at this point
Copy the full SHA 1e85c50View commit details -
include kl_loss() function in Convolutional flipout layers,
to compute kl when 'return_kl' flag is set to False. Fix for issue#12. Signed-off-by: Ranganath Krishnan <ranganath.krishnan@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 97ebe28 - Browse repository at this point
Copy the full SHA 97ebe28View commit details -
Configuration menu - View commit details
-
Copy full SHA for b0f928b - Browse repository at this point
Copy the full SHA b0f928bView commit details
Commits on Jan 13, 2022
-
Configuration menu - View commit details
-
Copy full SHA for f6cb161 - Browse repository at this point
Copy the full SHA f6cb161View commit details
Commits on Jan 17, 2022
-
Configuration menu - View commit details
-
Copy full SHA for ebd4bff - Browse repository at this point
Copy the full SHA ebd4bffView commit details
Commits on Jan 18, 2022
-
Configuration menu - View commit details
-
Copy full SHA for c6e6c09 - Browse repository at this point
Copy the full SHA c6e6c09View commit details -
Configuration menu - View commit details
-
Copy full SHA for 035460a - Browse repository at this point
Copy the full SHA 035460aView commit details
Commits on Jan 26, 2022
-
Configuration menu - View commit details
-
Copy full SHA for 1057bfb - Browse repository at this point
Copy the full SHA 1057bfbView commit details -
Configuration menu - View commit details
-
Copy full SHA for 7d20108 - Browse repository at this point
Copy the full SHA 7d20108View commit details -
Configuration menu - View commit details
-
Copy full SHA for bdd262e - Browse repository at this point
Copy the full SHA bdd262eView commit details
This comparison is taking too long to generate.
Unfortunately it looks like we can’t render this comparison for you right now. It might be too big, or there might be something weird with your repository.
You can try running this command locally to see the comparison on your machine:
git diff v0.1...v0.2.0