导入相应的包：
#这一行是我tensorflow的问题，其实不用导入import os os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'import numpy as npimport kerasfrom keras.models import Sequentialfrom keras.layers.core import Dense, Dropout, Activationfrom keras.layers import Convolution2D, MaxPooling2D, Flattenfrom keras.optimizers import SGD, Adamfrom keras.utils import np_utilsfrom keras.datasets import mnist
价值数据，因为mnist好像被墙了，所以是下载好数据放入MNIST_data文件夹之中的。
def load_data():
#网络下载失败
#(x_train, y_train), (x_test, y_test) = mnist.load_data('mnist.npz')
#读取本地数据
path = './mnist.npz'
f = np.load(path)
x_train, y_train = f['x_train'], f['y_train']
x_test, y_test = f['x_test'], f['y_test']
f.close()
number = 10000
x_train = x_train[0: number]
y_train = y_train[0: number]
x_train = x_train.reshape(number, 28 * 28)
x_test = x_test.reshape(x_test.shape[0], 28 * 28)
x_train = x_train.astype('float32')
x_test = x_train.astype('float32') # convert class vectors to binary class matrices
y_train = np_utils.to_categorical(y_train, 10)
y_test = np_utils.to_categorical(y_test, 10)
x_train = x_train
x_test = x_test # x_test = np.random.normal(x_test)
x_train = x_train / 255
x_test = x_test / 255
return (x_train, y_train), (x_test, y_test)第一次调试代码：
(x_train, y_train), (x_test, y_test) = load_data()#验证数据是够加载print(x_train.shape)#申明一个模型model = Sequential()
model.add(Dense(input_dim=28 * 28, units=689, activation='sigmoid'))
model.add(Dense(units=689, activation='sigmoid'))
model.add(Dense(units=689, activation='sigmoid'))
model.add(Dense(units=10, activation='softmax'))
model.compile(loss='mse', optimizer=SGD(lr=0.1), metrics=['accuracy'])#开始训练model.fit(x_train, y_train, batch_size=100, epochs=20)
result = model.evaluate(x_train, y_train, batch_size=10000)
print('\nTrain Acc:', result[1])
result = model.evaluate(x_test, y_test, batch_size=10000)
print('\nTest Acc:', result[1])结果：
image.png
第二次调试：
在训练集上表现都不好，没有训练起来，修改loss functon为categorical_crossentropy
# model.compile(loss='mse', optimizer=SGD(lr=0.1), metrics=['accuracy'])model.compile(loss='categorical_crossentropy', optimizer=SGD(lr=0.1), metrics=['accuracy'])
结果：已经训练起来了，overfitting
image.png
第三次调试：调整batch_size
结果：并不是越大越好，batch_size为1是没有调用GPU
第四次调试：deep，添加10层hidden layer
for i in range(10): model.add(Dense(units=689, activation='sigmoid')) model.add(Dense(units=10, activation='softmax'))
结果：training和testing都坏掉了：
image.png
第五次调试：修改activation，改为relu
relu可以避免神经网络后面过早收敛
model.add(Dense(input_dim=28 * 28, units=689, activation='relu'))for i in range(10): model.add(Dense(units=689, activation='relu')) model.add(Dense(units=10, activation='softmax'))
结果
image.png
第六次调试：加上dropout
#申明一个模型model = Sequential() model.add(Dense(input_dim=28 * 28, units=689, activation='relu')) model.add(Dropout(0.7)) model.add(Dense(units=689, activation='relu')) model.add(Dropout(0.7)) model.add(Dense(units=689, activation='relu')) model.add(Dropout(0.7))# for i in range(10):# model.add(Dense(units=689, activation='relu'))model.add(Dense(units=10, activation='softmax'))
结果：和上面差不多，并没有像老师演示的那样在testing set上也表现比较好，有没有大佬来给我讲讲！！！谢谢！！
作者：米特尼克大粉丝
链接：https://www.jianshu.com/p/72aeb368fa9e
随时随地看视频
