PyTorch-BayesianCNN
PyTorch-BayesianCNN copied to clipboard
kumar-shridhar
Bayesian Convolutional Neural Network with Variational Inference based on Bayes by Backprop in PyTorch.
Hi, thanks for your great work! I wonder if the GPU memory usage will grow linearly with the parameter "num_ens" in the code? If I increase "num_ens", there will be...
Hi, thanks for this nice work, I really appreciate it! I tried to replicate the results from your paper with the repository, but I have not succeeded. First, I downloaded...
https://github.com/kumar-shridhar/PyTorch-BayesianCNN/blob/d93bad543c3226cd0fe05c0cb0ba033c41b3caa6/main_bayesian.py#L116 Your training set is divided on train and validation. Shouldn't here be `(1-valid_size)*len(trainset)`?
I am trying to run uncertainty_estimation file with custom dataset but i am always getting the following error: using 3306 images for training, 364 images for validation. Traceback (most recent...
I am trying to replicate the results of the paper, and also extend it for segmentation. Why is "sample" always true for both training and validation passes in the forward...
Hey there, I recently tried to implement a Bayesian Net myself and oriented myself a little on your implementation. When coming across the computation of the epistemic and aleatoric, I...
 I see that you have multiple nllLoss with train_size. This makes the value of the loss is very large. I don't understand why do you do that? You can...
Can the prior distribution be arbitrarily set? In the CNN, the weight can be optimized by the back propagate. However, in the BCNN, the W_mu and W_sigma always seem to...
Hi, afer reading your paper, I think bayesian can be used for segmentation, then I add bayes into CNN by resampling weight and bias in conv3d, but the result is...
When I tried to run uncertainty_estimation.py, it had kept returned 503 Service Unavailable error. Since the link for downloading `mnist/train-labels-idx1-ubyte.gz` is unavailable now, would you change the code not to...
Metadata
Owner
Metadata
Bayesian Convolutional Neural Network with Variational Inference based on Bayes by Backprop in PyTorch.