ValueError：形状 (None, 10, 2, 2) 和 (None, 10) 不兼容

Question

我正在关注我最近得到的一本新书，但我遇到了这个错误，我不知道我做错了什么

ValueError：形状 (None, 10, 2, 2) 和 (None, 10) 不兼容

这是代码

from keras import models
from keras import layers

network = models.Sequential()
network.add(layers.Dense(512, activation='relu', input_shape=(28 * 28,)))
network.add(layers.Dense(10, activation='softmax'))

network.compile(optimizer = 'rmsprop', 
           loss = 'categorical_crossentropy', 
           metrics=['accuracy'])

train_images = train_images.reshape((60000, 28 * 28))
train_images = train_images.astype('float32') / 255

test_images = test_images.reshape((10000, 28 * 28))
test_images = test_images.astype('float32') / 255

from tensorflow.keras.utils import to_categorical

train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)

network.fit(train_images, train_labels, epochs=1, batch_size = 128)

Answer 1

您发布的代码看起来不错，我只是运行它。 有用。 我认为您在以正确方式导入数据集时遇到问题。 我使用 MNIST 数据集来测试您的代码，并在导入行前添加了注释。 尝试复制它并告诉我问题是否仍然存在。

from keras import models
from keras import layers
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.utils import to_categorical
from keras.datasets import mnist
from tensorflow.keras.utils import to_categorical

(train_X, train_y), (test_X, test_y) = mnist.load_data() # Load mnist
# I wrote train_X... but changed it later 

network = models.Sequential()
network.add(layers.Dense(512, activation='relu', input_shape=(28 * 28,)))
network.add(layers.Dense(10, activation='softmax'))

network.compile(optimizer = 'rmsprop', 
           loss = 'categorical_crossentropy', 
           metrics=['accuracy'])

train_images = train_X.reshape((60000, 28 * 28))
train_images = train_images.astype('float32') / 255

test_images = test_X.reshape((10000, 28 * 28))
test_images = test_images.astype('float32') / 255

train_labels = to_categorical(train_y)
test_labels = to_categorical(test_y)

network.fit(train_images, train_labels, epochs=1, batch_size = 128)

Answer 2

• 我已经使用 mnist 运行了代码，我认为问题在于您预处理train_labels的方式。 您可能正在将 function to_categorical()应用于导致维度错误的已分类数据。
• 打印train_labels的尺寸并确保其尺寸类似于(60000, 10) 。 60000 可能会有所不同，但元组中的第二个值应该是 10。