2021-08-20Fashion_mnist服饰预测

#数据加载
from keras.datasets import fashion_mnist
import numpy as np
(X_train,y_train),(X_test,y_test) = fashion_mnist.load_data()
print(type(X_train),X_train.shape)

#样本可视化
img1 = X_train[0]
#引入画图包
from matplotlib import pyplot as plt
fig1 = plt.figure(figsize=(3,3))
plt.imshow(img1)
plt.title('raw img 1')

#输入数据的预处理
feature_size = img1.shape[0]*img1.shape[1]
print(feature_size)
X_train_format = X_train.reshape(X_train.shape[0],feature_size)
X_test_format = X_test.reshape(X_test.shape[0],feature_size)
print(X_train_format.shape,X_train.shape)

#数据归一化
X_train_normal=X_train_format/255
X_test_normal=X_test_format/255
print(X_train_normal[0])

#输出结果的数据预处理
from keras.utils import to_categorical
y_train_format = to_categorical(y_train)
y_test_format = to_categorical(y_test)
print(y_train[0])
print(y_train_format[0])

#建立mlp模型
from keras.models import Sequential
from keras.layers import Dense, Activation

mlp = Sequential()
mlp.add(Dense(units = 392, input_dim = 784, activation='relu'))
mlp.add(Dense(units = 196, activation='relu'))
mlp.add(Dense(units=10, activation='softmax'))
mlp.summary()

#参数配置
mlp.compile(optimizer='adam',loss='categorical_crossentropy',metrics=['categorical_accuracy'])

#模型训练
mlp.fit(X_train_normal, y_train_format, epochs=10)

y_train_predict=mlp.predict_classes(X_train_normal)
print(y_train_predict[0:10])

#准确率
y_test_predict=mlp.predict_classes(X_test_normal)
accuracy_test=accuracy_score(y_test,y_test_predict)
print(accuracy_test)
from sklearn.metrics import accuracy_score
accuracy_train=accuracy_score(y_train,y_train_predict)
print(accuracy_train)

#创建结果标签
label_dict={0:'T shirt',1:'裤子',2:'套头衫',3:'裙子',4:'外套',5:'凉鞋',6:'衬衫',7:'运动鞋',8:'包',9:'踝靴'}
print(label_dict)

#样本可视化
img2=X_train[100]
fig2=plt.figure(figsize=(3,3))
plt.imshow(img2)

label_dict[y_train_predict[100]]

a = [i for i in range(1,10)]
print(a)
fig4=plt.figure(figsize=(5,5))
font2={'family':'SimHei'}
for i in a:
    plt.subplot(3,3,i)
    plt.imshow(X_test[i])
    plt.title('predict:{}'.format(label_dict[y_test_predict[i]]),font2)