explain make_optimizer() for beginners

[omiderfanmanesh]

I am new to PyTorch and I like your valuable project. to better understand, I will appreciate it if you explain that why you use a loop and extract all weights of the network in this function:

def make_optimizer(cfg, model):
    params = []
    for key, value in model.named_parameters():
        if not value.requires_grad:
            continue
        lr = cfg.SOLVER.BASE_LR
        weight_decay = cfg.SOLVER.WEIGHT_DECAY
        if "bias" in key:
            lr = cfg.SOLVER.BASE_LR * cfg.SOLVER.BIAS_LR_FACTOR
            weight_decay = cfg.SOLVER.WEIGHT_DECAY_BIAS
        params += [{"params": [value], "lr": lr, "weight_decay": weight_decay}]
    optimizer = getattr(torch.optim, cfg.SOLVER.OPTIMIZER_NAME)(params, momentum=cfg.SOLVER.MOMENTUM)
    return optimizer

and why don't you use simply this code e.g:

optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
optimizer = optim.Adam([var1, var2], lr=0.0001)