问题遇到的现象和发生背景
正在学《Python深度学习》一书,其中第五章有一个例子是用CNN的方法给MNIST数据集分类,我在用书本里的范例代码的时候出现了问题UnimplementedError: Graph execution error:
已知这个例子的tensorflow版本是2.0,我的是2.8,可能是版本问题,可以问一下应该怎么修改吗?出现问题的原因是什么呢?谢谢
问题相关代码,请勿粘贴截图
#Simple CNN
from keras import layers
from keras import models
model = models.Sequential()
model.add(layers.Conv2D(32, (3,3), activation = 'relu', input_shape = (28, 28, 1)))
model.add(layers.MaxPooling2D((2,2)))
model.add(layers.Conv2D(64, (3,3), activation = 'relu'))
model.add(layers.MaxPooling2D((2,2)))
model.add(layers.Conv2D(64, (3,3), activation = 'relu'))
model.add(layers.Flatten())
model.add(layers.Dense(64, activation = 'relu'))
model.add(layers.Dense(10, activation = 'softmax'))
model.summary()
Test this model on mnist
from keras.datasets import mnist
from tensorflow.keras.utils import to_categorical
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
train_images = train_images.reshape((60000,28,28,1))
train_images = train_images.astype('float32')/255
test_images = test_images.reshape((10000,28,28,1))
test_images = test_images.astype('float32')/255
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)
model.compile(optimizer = 'rmsprop', loss = 'categorical_crossentropy', metrics = ['accuracy'])
model.fit(train_images, train_labels, epochs=5, batch_size=64)
运行结果及报错内容
Epoch 1/5
UnimplementedError Traceback (most recent call last)
(此处省略)
UnimplementedError: Graph execution error:
我的解答思路和尝试过的方法
我尝试过改loss function 成sparse_categorical_crossentropy,不过报错结果还是一样,其他的我真的不知道怎么回事了,这是范例代码,应该是没问题的。
我想要达到的结果
跑通就行