Tensorflow ValueError:层sequential_22的输入0与层不兼容：预期ndim=4，发现ndim=3。收到完整形状：[28,28,1]

我得到一个错误：

---

ValueError:层sequential_22的输入0与层不兼容：预期ndim=4，发现ndim=3。收到完整形状：[28,28,1]

添加输入形状，拟合功能。不要发布不完整的代码让别人猜。我做了更改。谢谢你，你的代码运行非常好，没有任何问题。对不起。这是一种时尚，没有mnist数据。我与mnist没有任何问题。Fashion_mnist表示错误添加输入形状、贴合功能。不要发布不完整的代码让别人猜。我做了更改。谢谢你，你的代码运行非常好，没有任何问题。对不起。这是一种时尚，没有mnist数据。我与mnist没有任何问题。时尚专家说这是个错误

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'))

from keras.datasets import mnist
from keras.utils import to_categorical
(train_images, train_labels), (test_images, test_labels) = fashion_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)