Bayesian-Neural-Networks

Bayesian-Neural-Networks copied to clipboard

Question: log_gaussian_loss function used in MC Dropout and SGLD

1

Firstly, thank you for all these great notebooks, they've been very helpful in building a better understanding of these methods. I am wondering where the function `log_gaussian_loss` originates from? I'm...

acse-aol21

May I ask the code about calculating the Hessian in the Kronecker-Factorised Laplace methods?

1

def softmax_CE_preact_hessian(last_layer_acts): side = last_layer_acts.shape[1] I = torch.eye(side).type(torch.ByteTensor) # for i != j H = -ai * aj -- Note that these are activations not pre-activations Hl = - last_layer_acts.unsqueeze(1)...

zehuanzhang

code implementation

1

Thank you for the code. How can i run in cpu? the code only support CUDA? Regards

sujanme25

[Question][MC dropout] drop hidden units for each data point or for each mini-batch data?

1

Hi JavierAntoran, Thanks for the wonderful code first, and it is really helpful for me working in the related area. I'd like to consult a question about the MC dropout....

alwaysuu

Panda not reading the first row

1

Minor bug. Instead of: data = pd.read_csv('housing.data', header=0, delimiter="\s+").values Use: data = pd.read_csv('housing.data', header=None, delimiter="\s+").values

caxelrud

[Question] BBB vs BBB w/ Local Reparameterization

4

Hi @JavierAntoran @stratisMarkou, First of all, thanks for making all of this code available - it's been great to look through! Im currently spending some time trying to work through...

danielkelshaw

2 questions: batch & layer

1

Here are two questions, and would you please help me with them: 1. In the COLAB notebook, this code didn't train in batches, right? 2. In the COLAB notebook, the...

EvannaB