机器学习笔记(2)：线性回归-使用gluon

代码来自：https://zh.gluon.ai/chapter_supervised-learning/linear-regression-gluon.html

 from mxnet import ndarray as nd
 from mxnet import autograd
 from mxnet import gluon

 num_inputs = 2
 num_examples = 1000

 true_w = [2, -3.4]
 true_b = 4.2

 X = nd.random_normal(shape=(num_examples, num_inputs)) #1000行，2列的数据集
 y = true_w[0] * X[:, 0] + true_w[1] * X[:, 1] + true_b #已知答案的结果
 y += .01 * nd.random_normal(shape=y.shape) #加入噪音

 #1 随机读取10行数据
 batch_size = 10
 dataset = gluon.data.ArrayDataset(X, y)
 data_iter = gluon.data.DataLoader(dataset, batch_size, shuffle=True)

 #2 定义回归模型
 net = gluon.nn.Sequential()
 net.add(gluon.nn.Dense(1))

 #3 参数初始化
 net.initialize()

 #4 损失函数
 square_loss = gluon.loss.L2Loss()

 #5 指定训练方法
 trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.1})

 #6 训练
 epochs = 5
 batch_size = 10
 for e in range(epochs):
     total_loss = 0
     for data, label in data_iter:
         with autograd.record():
             output = net(data)
             loss = square_loss(output, label)
         loss.backward()
         trainer.step(batch_size)
         total_loss += nd.sum(loss).asscalar()
     print("Epoch %d, average loss: %f" % (e, total_loss/num_examples))

 #7 输出结果
 dense = net[0]
 print(true_w)
 print(dense.weight.data())
 print(true_b)
 print(dense.bias.data())

相对上一篇纯手动的处理方式，用gluon后代码明显更精简了。