Rishav09

System Design Cheatsheet

Picking the right architecture = Picking the right battles + Managing trade-offs

Basic Steps

1. Clarify and agree on the scope of the system

• User cases (description of sequences of events that, taken together, lead to a system doing something useful)
  • Who is going to use it?
  • How are they going to use it?

Rishav09

        model.train()
        for batch_idx, (data, target) in enumerate(loader['train']):
            # move to GPU
            if torch.cuda.is_available():
                data, target = data.to('cuda', non_blocking=True), target.to('cuda', non_blocking = True) # noqa
            optimizer.zero_grad()
            output = model(data)
            pred = torch.argmax(output, dim=1)
            # pred = pred.to(torch.double)
            # target = target.to(torch.double)