Gullal Cheema

@KarenUllrich The network trains fine for convolution layers, but the compression.py functions do not work for convolutional weights/filters. I have made some changes in the compute_posterior_params to compute post_weight_mu and...

You will need to make some changes in BayesianLayers.py and get_masks() function to prune the conv layers. With the current code, you can only prune linear layers. ``` def compute_posterior_params(self):...

Sure. This is the get_masks() function I am using. Basically incorporating the difference in size of weights in conv layers and linear layers, as done in compute posterior params. Secondly,...

Unfortunately with a larger network like VGG, loss becomes nan because of vanishing gradients problem. I believe only authors can help in this case.

I have tried output:0 with the following command: `mmconvert -sf tensorflow -in snapshot-55.meta -iw snapshot-55 --dstNode output:0 -df pytorch -om serengeti_resnet_152.pth` but it gives me the error that node is...

You could use custom dataset class and use dataloader to do batching. This is how I run it and it is quite fast. ``` class CustomDataset(Dataset): def __init__(self, image_folder, prompt,...

I was also facing the same issue (on Linux) and found a solution after looking at the prototxt files in the models folder. The location for respective (e.g. in solver_60k80k.prototxt)...