Saravanabalagi Ramachandran

Hi @janthmueller, thanks for the workaround, I tried that but the network comes back with only the last conv layer pruned. No dep group with first conv layer is being...

Great, thanks for the workaround and the explanation! It would be great to have this merged such that the lib works directly on GLU!

Direct update sparsity during speedup includes a [step](https://github.com/microsoft/nni/blob/8dc1a8304722487107ad4c4f2f059c26e7b5a5b6/nni/compression/pytorch/speedup/v2/model_speedup.py#L197) that calculates standard deviation of outputs at the batch dimension i.e., deviation compared with other batches of data is measured and all...

While it makes sense to mask weights corresponding to the output positions where std dev is close to 0 for speedup, this is not mentioned and/or explained in the docs....

Hi @zedtux, thanks for the pull request in the rails library, this was probably long awaited by many users! I initially copied the compiled code to make quick changes for...

The error is thrown specifically when the output channels of the last layer is 1, even when there are 2 successive conv blocks: ```python class ConvNet(nn.Module): def __init__(self): super().__init__() self.relu...

> Hi @jessesanford and thanks for your help! > Before merging the PR, could you explain me how to reproduce the problem? 😃 1. Create a new rails 5 api...

@Didayolo Any update on a fix for adding new pages?

CSV files without a header row. E.g. a similarity matrix saved as a CSV/TSV where we would look up values at (row, col).

Also when using lightning, I get: N812 Lowercase `lightning` imported as non-lowercase `L`