Commit a516d79

committed

Update README.md

1 parent 9bf3b03 commit a516d79Copy full SHA for a516d79

File tree

-4

lines changed

-4

lines changed

Lines changed: 1 addition & 4 deletions

Original file line number	Diff line number	Diff line change
`@@ -31,14 +31,11 @@ import torchbnn`
`31`	`31`	`* modules : BayesLinear, BayesConv2d, BayesBatchNorm2d`
`32`	`32`	`* utils : convert_model(nonbayes_to_bayes, bayes_to_nonbayes)`
`33`	`33`	`* functional : bayesian_kl_loss`
`34`		`-<<<<<<< HEAD`
`35`	`34`
`36`	`35`	`### Version 0.2`
`37`	`36`	`* prior_sigma is used when initialize modules and functions instead of prior_log_sigma`
`38`	`37`	`* Modules(BayesLinear, BayesConv2d, BayesBatchNorm2d) are re-defined with prior_sigma instead of prior_log_sigma.`
`39`	`38`	`* convert_model(nonbayes_to_bayes, bayes_to_nonbayes) is also changed with prior_sigma instead of prior_log_sigma.`
`40`	`39`	`* Modules(BayesLinear, BayesConv2d, BayesBatchNorm2d) : Base initialization method is changed to the method of Adv-BNN from the original torch method.`
`41`	`40`	`* functional : bayesian_kl_loss is changed similar to ones in torch.functional`
`42`		`-* loss : BKLLoss is added based on bayesian_kl_loss similar to ones in torch.loss`
`43`		`-=======`
`44`		`->>>>>>> 8be43015d291edb1fc413d4ec25e21d238374f70`
	`41`	`+* loss : BKLLoss is added based on bayesian_kl_loss similar to ones in torch.loss`

Comments

(0)