Aditya Oke

Yes, what would happen at places is our `model.py` file gets too lengthy, and creates tons of code duplication for common blocks, activation functions. If we could collectively place them...

Question is how to determine if certain block is `layer`, `component` or should be part of model. A high level logic. If we are pretty sure that a block of...

Yes, Detr is using `torch.hub`. I could not implement from scratch and Detr transfer learning differs from training, so it becomes quite hard to replicate. `torch.hub` is very nice approach...

I suggest when people add new models, they might not have idea of how these stuff work. Let them write model as follows ``` model_folder ----- __init__.py (whaterer we can...

Somehow I understand that decomposition kind of distributes our code here and there, but I think it will be only upto this level. But this keeps flexibility, again authors who...

Again @zhiqwang aim is not to go into such super hyper details, we use layers which are used by papers, most use a simple version of mish and not so...

@digantamisra98 people are free to use Echo along with this, since adding Echo will add it's sub depedencies which will probably bulk up this library. It would also be hard...

Another point with this API. I think we should discourage the use `functional` API in our case for layers. Reason 1. Blocks such as MLP, CSPNet do not have any...

A possible fix is to get number of classes from dataloader, and pass `topk` as ``` if dataloader.num_classes < 5: acc1, acck = topk(1, num_classes) else: acc1, acck = topk(1,...

Yes definitely I will fix this up, this is very trivial bug. Once its fixed you can install from master :smile: and get the latest update