def make_optimizer()

in scripts/train_instance_seg.py [0:0]

• 32 lines of code
• 14 McCabe index (conditional complexity)

def make_optimizer(config, model, epoch_length):
    body_config = config["body"]
    opt_config = config["optimizer"]
    sch_config = config["scheduler"]

    # Gather parameters from the network
    norm_parameters = []
    other_parameters = []
    for m in model.modules():
        if any(isinstance(m, layer) for layer in NORM_LAYERS):
            norm_parameters += [p for p in m.parameters() if p.requires_grad]
        elif any(isinstance(m, layer) for layer in OTHER_LAYERS):
            other_parameters += [p for p in m.parameters() if p.requires_grad]
    assert len(norm_parameters) + len(other_parameters) == len([p for p in model.parameters() if p.requires_grad]), \
        "Not all parameters that require grad are accounted for in the optimizer"

    # Set-up optimizer hyper-parameters
    parameters = [
        {
            "params": norm_parameters,
            "lr": opt_config.getfloat("lr") if not body_config.getboolean("bn_frozen") else 0.,
            "weight_decay": opt_config.getfloat("weight_decay") if opt_config.getboolean("weight_decay_norm") else 0.
        },
        {
            "params": other_parameters,
            "lr": opt_config.getfloat("lr"),
            "weight_decay": opt_config.getfloat("weight_decay")
        }
    ]

    optimizer = optim.SGD(
        parameters, momentum=opt_config.getfloat("momentum"), nesterov=opt_config.getboolean("nesterov"))

    scheduler = scheduler_from_config(sch_config, optimizer, epoch_length)

    assert sch_config["update_mode"] in ("batch", "epoch")
    batch_update = sch_config["update_mode"] == "batch"
    total_epochs = sch_config.getint("epochs")

    return optimizer, scheduler, batch_update, total_epochs