softmax回归的从零实现

# softmax回归的从零开始
%matplotlib inline
import d2lzh as d2l
from mxnet import autograd, nd

# 定义迭代器
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

# 定义输出与输入大小
num_inputs = 784
num_outputs = 10

# 初始化权重
W = nd.random.normal(scale=0.01,shape=(num_inputs,num_outputs))
b = nd.zeros(num_outputs)

# 为W,b开辟求梯度的内存
W.attach_grad()
b.attach_grad()

# 定义softmax
def softmax(X):
    X_exp = X.exp()
    partition = X_exp.sum(axis=1,keepdims=True)
    return X_exp / partition

# 定义模型
def net(X):
    return softmax(nd.dot(X.reshape(-1,num_inputs), W) + b)


# 定义交叉熵损失函数
# y_hat为预测值，y为标签类别（例如0，1，2等）
# pick(x,y)：返回x中索引为y的值
def cross_entropy(y_hat, y):
    return -nd.pick(y_hat, y).log()


# 模型评价
def evaluate_accuracy(data_iter, net):
    acc_sum, n = 0.0, 0
    for x, y in data_iter:
        y = y.astype('float32')
        acc_sum += (net(x).argmax(axis=1) == y).sum().asscalar()
        n += y.size
    return acc_sum / n

# 开始训练-------------------------------------------------------------------------------
num_epochs, lr = 5, 0.1

def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, 
              params=None, lr=None, trainer=None):# trainer为优化方法
    for epoch in range(num_epochs):
        train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
        for x,y in train_iter:# train_iter 
            with autograd.record():
                y_hat = net(x)
                l = loss(y_hat, y).sum()
            l.backward()
            if trainer is None:
                d2l.sgd(params, lr, batch_size)
            else:
                trainer.step(batch_size)
            y = y.astype('float32')
            train_l_sum += l.asscalar()
            train_acc_sum += (y_hat.argmax(axis=1)==y).sum().asscalar()
            n += y.size
        test_acc = evaluate_accuracy(test_iter, net)
        print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f' %(epoch + 1, train_l_sum/n, train_acc_sum/n, test_acc))

train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, batch_size, [W, b], lr)

# 预测-----------------------------------------------------------------------------------
for x,y in test_iter:
    break
# get_fashion_mnist_label用来将 标签类别 转换为 对应的文字
true_labels = d2l.get_fashion_mnist_labels(y.asnumpy())
pred_labels = d2l.get_fashion_mnist_labels(net(x).argmax(axis=1).asnumpy())
titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]

# 用来显示图片x和对应的标签
d2l.show_fashion_mnist(x[0:9],titles[0:9])