Mostafa Elhoushi

I have created a pull request to address this issue: https://github.com/sksq96/pytorch-summary/pull/88

Thanks @Naireen According to the link you sent provided, I am quoting the following: > Also by default, during training this layer keeps running estimates of its computed mean and...

I am willing to implement this feature, but couldn't assign the issue to myself.

Did you try to train for one epoch with learning rate = 0 (`--lr 0`)?

Just quoting from this [blog article](https://blog.paperspace.com/popular-deep-learning-architectures-alexnet-vgg-googlenet/): > The model uses a stochastic gradient descent optimization function with batch size, momentum, and weight decay set to 128, 0.9, and 0.0005 respectively....

Maybe try those hyperparameters, and if they lead to the expected accuracy, perhaps create a pull request to update the README file accordingly?

> So far our tests aren't in a place where we can guarantee some model performance, the case could be made that maybe we should? But so far we don't...

First of all, thanks for your quick response, I highly appreciate that! I originally tired with `epochs` setting kept at 4. I changed it to 5 and waiting for the...

Thanks Maxim for your detailed response. I have also tried training with 5 epochs per iteration and used the batch size and other hyperparameters they mentioned in their paper for...

> Hi @mostafaelhoushi, were you able to solve the problem in the end or no? > I am not able to reproduce the results for 2 bits weight for ResNet18....