You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+9-1Lines changed: 9 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -20,6 +20,10 @@ To help construct bayesian neural network intuitively, all codes are modified ba
20
20
import torchbnn
21
21
```
22
22
23
+
### Demos
24
+
***Bayesian Neural Network with Iris Data** ([code](https://github.com/Harry24k/bayesian-neural-network-pytorch/blob/master/demos/White%20Box%20Attack%20with%20Imagenet.ipynb)):
25
+
To classify Iris data, in this demo, two-layer bayesian neural network is constructed and tested with plots. It shows how bayesian-neural-network works and randomness of the model.
***modules** : For supporting **freeze** method, freeze, weight_eps and bias_eps is added to each modules. If freeze is False (Defalt), weight_eps and bias_eps will be initialized with normal noise at every forward. If freeze is True, weight_eps and bias_eps won't be changed.
59
63
60
64
### Version 0.7
65
+
***DO NOT USE**
66
+
67
+
### Version 0.8
61
68
***modules** : For supporting **freeze** method, weight_eps and bias_eps is changed to buffer with register_buffer method. Thorugh this change, it provides save and load even if bayesian neural network is freezed.
62
69
***BayesModule is added** : Bayesian version of torch.nn.Module. Not being used currently.
63
70
***utils/freeze_model.py** :
64
-
***freeze, unfreeze methods are modified** : Previous methods didn't work on single layer network.
71
+
***freeze, unfreeze methods are modified** : Previous methods didn't work on single layer network.
72
+
***Demos are uploaded** : "Bayesian Neural Network with Iris Data".
0 commit comments