How to use the autogluon.space function in autogluon

def test_custom_optim_range():
    logger.debug('Start custom optimizer range')
    opt = ag.optimizers.Adam(lr=ag.space.Log('lr', 10 ** -2, 10 ** -1),
                             wd=ag.space.Log('wd', 10 ** -6, 10 ** -2))
    logger.debug(opt.hyper_params)
    logger.debug('Finished.')

def test_log_space():
    logger.debug('Start testing log space')
    log_space = ag.space.Log('logspace', 10**-10, 10**-1)
    print(log_space)
    logger.debug('Finished.')

    wd=ag.space.Categorical(1e-3, 1e-2))
def rl_train_fn(args, reporter):
    for e in range(10):
        dummy_accuracy = 1 - np.power(1.8, -np.random.uniform(e, 2*e))
        reporter(epoch=e, accuracy=dummy_accuracy, lr=args.lr, wd=args.wd)

def test_custom_optim_range():
    logger.debug('Start custom optimizer range')
    opt = ag.optimizers.Adam(lr=ag.space.Log('lr', 10 ** -2, 10 ** -1),
                             wd=ag.space.Log('wd', 10 ** -6, 10 ** -2))
    logger.debug(opt.hyper_params)
    logger.debug('Finished.')

    c=ag.space.Int(1, 10),
    d=ag.space.Categorical('a', 'b', 'c', 'd'),
    e=ag.space.Bool(),
    f=ag.space.List(
            ag.space.Int(1, 2),
            ag.space.Categorical(4, 5),
        ),
    g=ag.space.Dict(
            a=ag.Real(0, 10),
            obj=myobj(),
        ),
    h=ag.space.Categorical('test', myobj()),
    i = myfunc(),
    )
def train_fn(args, reporter):
    a, b, c, d, e, f, g, h, i = args.a, args.b, args.c, args.d, args.e, \
            args.f, args.g, args.h, args.i

    framework=ag.space.Categorical('mxnet', 'pytorch'),
)
def myfunc(framework):
    return framework

def test_list_space():
    logger.debug('Start testing list space')
    list_space = ag.space.List('listspace', ['0',
                                             '1',
                                             '2'])
    print(list_space)
    logger.debug('Finished.')

import math
import autogluon as ag
from autogluon import ImageClassification as task

@ag.obj(
    width_coefficient=ag.space.Categorical(1.1, 1.2),
    depth_coefficient=ag.space.Categorical(1.1, 1.2),
)
class EfficientNetB1(ag.nas.EfficientNet):
    def __init__(self, width_coefficient, depth_coefficient):
        input_factor = math.sqrt(2.0 / (width_coefficient ** 2) / depth_coefficient)
        input_size = math.ceil((224 * input_factor) / 32) * 32
        super().__init__(width_coefficient=width_coefficient,
                         depth_coefficient=depth_coefficient,
                         input_size=input_size)

results = task.fit('imagenet', net=EfficientNetB1(), search_strategy='grid',
                   optimizer=ag.optimizer.SGD(learning_rate=1e-1,momentum=0.9,wd=1e-4),
                   batch_size=32)

print(results)

import math
import autogluon as ag
from autogluon import ImageClassification as task

@ag.obj(
    width_coefficient=ag.space.Categorical(1.1, 1.2),
    depth_coefficient=ag.space.Categorical(1.1, 1.2),
)
class EfficientNetB1(ag.nas.EfficientNet):
    def __init__(self, width_coefficient, depth_coefficient):
        input_factor = math.sqrt(2.0 / (width_coefficient ** 2) / depth_coefficient)
        input_size = math.ceil((224 * input_factor) / 32) * 32
        super().__init__(width_coefficient=width_coefficient,
                         depth_coefficient=depth_coefficient,
                         input_size=input_size)

results = task.fit('imagenet', net=EfficientNetB1(), search_strategy='grid',
                   optimizer=ag.optimizer.SGD(learning_rate=1e-1,momentum=0.9,wd=1e-4),
                   batch_size=32)

print(results)

    lr=ag.space.Real(1e-2, 1e-1, log=True),
    momentum=0.9,
    wd=ag.space.Real(1e-5, 1e-3, log=True),
    epochs=20,
)
def train_cifar(args, reporter):
    print('args', args)
    batch_size = args.batch_size

    num_gpus = args.num_gpus
    batch_size *= max(1, num_gpus)
    context = [mx.gpu(i) for i in range(num_gpus)] if num_gpus > 0 else [mx.cpu()]
    num_workers = args.num_workers

    model_name = args.model
    net = get_model(model_name, classes=10)