NameError: name ‘num_classes‘ is not defined

代码来源：深度学习12.2函数式模型 

运行平台：jupyter(python3.10,tensorflow2.x) 

源码如下： 

import keras
from keras.datasets import mnist
from keras.layers import Input, Dense
from keras.models import Model

(trainX, trainY), (testX, testY) = mnist.load_data()
# 将图像像素转化为0到1之间的实数
trainX = trainX.astype('float32')
testX = testX.astype('float32')
trainX /= 255.0
testX /= 255.0
# 将标准答案转化为独热编码格式
trainY = keras.utils.to_categorical(trainY, num_classes)
testY = keras.utils.to_categorical(testY, num_classes) 
trainX = trainX.reshape(trainX.shape[0], img_rows*img_cols)
testX = testX.reshape(testX.shape[0], img_rows*img_cols)
inputs = Input(shape=(784,))
x = Dense(500, activation='relu')(inputs)
predictions = Dense(10, activation='softmax')(x)
model = Model(inputs=inputs, outputs=predictions)
#定义损失函数、优化函数和测试方法。
model.compile(loss=keras.losses.categorical_crossentropy, 
              optimizer=keras.optimizers.SGD(), metrics=['accuracy'])
#训练模型
model.fit(trainX, trainY, batch_size=128, epochs=20, 
	          validation_data=(testX, testY))
score = model.evaluate(testX, testY, batch_size=batch_size)
print('Test loss:{}'.format(score[0]))
print('Test accuracy:{}'.format(score[1]))

 

修改代码：

增加以下部分，即为定义处值。

num_classes = 10#分类种类
batch_size=100#每个批次的大小

import keras
from keras.datasets import mnist
from keras.layers import Input, Dense
from keras.models import Model
num_classes = 10#分类种类
batch_size=100#每个批次的大小
(trainX, trainY), (testX, testY) = mnist.load_data()
# 将图像像素转化为0到1之间的实数
trainX = trainX.astype('float32')
testX = testX.astype('float32')
trainX /= 255.0
testX /= 255.0
# 将标准答案转化为独热编码格式
trainY = keras.utils.to_categorical(trainY,num_classes)

testY = keras.utils.to_categorical(testY,num_classes) 
trainX = trainX.reshape(trainX.shape[0], img_rows*img_cols)
testX = testX.reshape(testX.shape[0], img_rows*img_cols)
inputs = Input(shape=(784,))
x = Dense(500, activation='relu')(inputs)
predictions = Dense(10, activation='softmax')(x)
model = Model(inputs=inputs, outputs=predictions)
#定义损失函数、优化函数和测试方法。
model.compile(loss=keras.losses.categorical_crossentropy, 
              optimizer=keras.optimizers.SGD(), metrics=['accuracy'])
#训练模型
model.fit(trainX, trainY, batch_size=128, epochs=20, 
	          validation_data=(testX, testY))
score = model.evaluate(testX, testY, batch_size=batch_size)
print('Test loss:{}'.format(score[0]))
print('Test accuracy:{}'.format(score[1]))

效果展示：