在MXNet中進行超參數調優有多種方法，其中常用的包括Grid Search（網格搜索）、Random Search（隨機搜索）和Bayesian Optimization（貝葉斯優化）等。

1. Grid Search（網格搜索）：Grid Search 是一種窮舉搜索的方法，通過定義一個超參數的取值范圍，對每個超參數進行組合，然后訓練模型并評估性能。可以通過MXNet的GridSearch類來實現。

from mxnet.gluon import nn
from mxnet.gluon.data.vision import transforms
from mxnet import autograd, gluon, init, nd
from mxnet.gluon import data as gdata, loss as gloss
from mxnet import metric as mtr
import mxnet as mx
import random
import time
import sys

grid_search = GridSearch({
    'learning_rate': [0.01, 0.1, 0.5],
    'momentum': [0.9, 0.95, 0.99],
    'batch_size': [32, 64, 128]
})

for params in grid_search:
    net = nn.Sequential()
    net.add(nn.Dense(128, activation='relu'),
            nn.Dense(64, activation='relu'),
            nn.Dense(10))
    net.initialize(init=init.Xavier())
    trainer = gluon.Trainer(net.collect_params(), 'sgd',
                            {'learning_rate': params['learning_rate'],
                            'momentum': params['momentum']})
    train(net, train_iter, test_iter, batch_size=params['batch_size'],
          trainer=trainer, num_epochs=num_epochs)

2. Random Search（隨機搜索）：Random Search 是一種隨機搜索的方法，通過在指定的超參數范圍內隨機采樣，然后訓練模型并評估性能。可以通過MXNet的RandomSearch類來實現。

from mxnet.gluon.contrib.model_zoo import get_model
from mxnet.gluon.data import vision
from mxnet.gluon.data.vision import transforms

random_search = RandomSearch({
    'learning_rate': (0.001, 0.1),
    'momentum': (0.5, 0.99),
    'batch_size': (32, 128)
})

for params in random_search:
    net = get_model('resnet18_v1', classes=10)
    net.initialize(init=init.Xavier())
    trainer = gluon.Trainer(net.collect_params(), 'sgd',
                            {'learning_rate': params['learning_rate'],
                            'momentum': params['momentum']})
    train(net, train_iter, test_iter, batch_size=params['batch_size'],
          trainer=trainer, num_epochs=num_epochs)

3. Bayesian Optimization（貝葉斯優化）：Bayesian Optimization 是一種基于貝葉斯優化的方法，通過在先前的結果中選擇最有希望的超參數進行下一次探索。可以使用第三方庫如BayesOpt進行Bayesian Optimization。

from bayes_opt import BayesianOptimization

def train_net(learning_rate, momentum, batch_size):
    net = nn.Sequential()
    net.add(nn.Dense(128, activation='relu'),
            nn.Dense(64, activation='relu'),
            nn.Dense(10))
    net.initialize(init=init.Xavier())
    trainer = gluon.Trainer(net.collect_params(), 'sgd',
                            {'learning_rate': learning_rate, 'momentum': momentum})
    train(net, train_iter, test_iter, batch_size=batch_size,
          trainer=trainer, num_epochs=num_epochs)
    return accuracy

optimizer = BayesianOptimization(
    f=train_net,
    pbounds={'learning_rate': (0.001, 0.1),
             'momentum': (0.5, 0.99),
             'batch_size': (32, 128)}
)

optimizer.maximize(init_points=5, n_iter=10)
best_params = optimizer.max['params']