MXNET深度学习框架-16-使用gluon实现dropout

        上一章从0开始实现了dropout方法，已经dropout应用在mlp中的实例，本章我们使用gluon实现带有dropout的mlp：

import mxnet.gluon as gn
import mxnet.autograd as ag
import mxnet.ndarray as nd
import mxnet.gluon as gn



'''---模型训练实例(引入dropout)---'''
# 预处理
def transform(data, label):
    return data.astype("float32") / 255, label.astype("float32")  # 样本归一化


mnist_train = gn.data.vision.FashionMNIST(train=True)
mnist_test = gn.data.vision.FashionMNIST(train=False)
data, label = mnist_train[0:9]
print(data.shape, label)  # 查看数据维度
import matplotlib.pyplot as plt


def show_image(image):  # 显示图像
    n = image.shape[0]
    _, figs = plt.subplots(1, n, figsize=(15, 15))
    for i in range(n):
        figs[i].imshow(image[i].reshape((28, 28)).asnumpy())
    plt.show()


def get_fashion_mnist_labels(labels):  # 显示图像标签
    text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat',
                   'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']
    return [text_labels[int(i)] for i in labels]

#
# show_image(data)
# print(get_fashion_mnist_labels(label))

'''----数据读取----'''
batch_size = 100
transformer = gn.data.vision.transforms.ToTensor()
train_data = gn.data.DataLoader(dataset=mnist_train, batch_size=batch_size, shuffle=True)
test_data = gn.data.DataLoader(dataset=mnist_test, batch_size=batch_size, shuffle=False)

'''----初始化模型参数----'''

'''----定义模型----'''

dropout1,dropout2=0.2,0.5
net=gn.nn.Sequential()
net.add(gn.nn.Dense(256,activation="relu"),
        gn.nn.Dropout(dropout1),
        gn.nn.Dense(128, activation="relu"),
        gn.nn.Dropout(dropout2),
        gn.nn.Dense(10)
        )
net.initialize()



# softmax和交叉熵损失函数
# 由于将它们分开会导致数值不稳定(前两章博文的结果可以对比)，所以直接使用gluon提供的API
cross_loss=gn.loss.SoftmaxCrossEntropyLoss()

# 定义准确率
def accuracy(output,label):
    return nd.mean(output.argmax(axis=1)==label).asscalar()

def evaluate_accuracy(data_iter,net):# 定义测试集准确率
    acc=0
    for data,label in data_iter:
        data,label=transform(data,label)
        output=net(data)  # 测试的时候dropout必须为0
        acc+=accuracy(output,label)
    return acc/len(data_iter)

# softmax和交叉熵分开的话数值可能会不稳定
cross_loss=gn.loss.SoftmaxCrossEntropyLoss()
# 优化
train_step=gn.Trainer(net.collect_params(),'sgd',{"learning_rate":0.1})

# 训练
lr=0.1
epochs=20
for epoch in range(epochs):
    train_loss=0
    train_acc=0
    for image,y in train_data:
        image,y=transform(image,y) # 类型转换，数据归一化
        with ag.record():
            output = net(image)
            loss = cross_loss(output, y)
        loss.backward()
        train_step.step(batch_size)
        train_loss += nd.mean(loss).asscalar()
        train_acc += accuracy(output, y)
    test_acc = evaluate_accuracy(test_data, net)
    print("Epoch %d, Loss:%f, Train acc:%f, Test acc:%f"
          %(epoch,train_loss/len(train_data),train_acc/len(train_data),test_acc))
'''----预测-------'''
# 训练完成后，可对样本进行预测
image_10,label_10=mnist_test[:10] #拿到前10个数据
show_image(image_10)
print("真实样本标签：",label_10)
print("真实数字标签对应的服饰名：",get_fashion_mnist_labels(label_10))

image_10,label_10=transform(image_10,label_10)
predict_label=net(image_10).argmax(axis=1)
print("预测样本标签：",predict_label.astype("int8"))
print("预测数字标签对应的服饰名：",get_fashion_mnist_labels(predict_label.asnumpy()))

训练结果：