Naireen Hussain

R: @reuvenlax

``` class TestMod(nn.Module): def __init__(self, input_size, attention_size, eps=0.0): super().__init__() self.weight = nn.Parameter(torch.Tensor(attention_size, input_size)) nn.init.kaiming_uniform_(self.weight, a=math.sqrt(5)) def forward(self, x): return self.weight test = TestMod(2,3) # print(list(test.named_parameters())) summary(test, ((1, 2))) ``` yeilds...

@sungjaechi this should now work with the new version of pytorch-summary (note that you'll have to clone it, not install it via pip). Let me know if it solves your...

@jayleverett, does this command work for you? `summary(model, (1, 512))`, as the following code snippit works with the current version of torchsummary on github. The one at the front is...

HI @TylerYep, I've been one of the maintainers of this project, and now currently have some time to be able to devote to this. If you're interested, I can work...

Slack is the main platform comes to mind, though I'm open to any alternative suggestions!

Sent, let me know if you receive it!

This isn't included since running_mean and running_var are what are used to determine what the learnable parameters (in this came beta and gamma). They aren't really learnable parameters. Here are...

I'm not entirely sure what that is happening, but you can get around the issue with this model structure instead. Notice that you no longer use the attributes group1 and...

This is because `ScriptModules` (what `fasterrcnn_resnet50_fpn` is represented as here) doesn't currently support forward hooks, and torchsummary currently assumes that the model passed in inherits from `nn.Module`, so then the...