数据基数不明确（确保所有数组包含相同数量的样本）

在使用数据集时，需要确认所有数组包含的样本数相同，避免出现“数据基数不明确”的错误。示例如下：

错误示例：

import numpy as np
from tensorflow.keras.utils import to_categorical

# 生成数据
x_train = np.random.random((100, 20, 30))
y_train = np.random.randint(10, size=(100,))   
y_train = to_categorical(y_train)  # 将标签one-hot编码

x_val = np.random.random((50, 20, 30))
y_val = np.random.randint(10, size=(60,))  # 样本数不同
y_val = to_categorical(y_val)

# 构建模型
model = keras.models.Sequential([
    keras.layers.Flatten(input_shape=(20, 30)),
    keras.layers.Dense(128, activation='relu'),
    keras.layers.Dense(10, activation='softmax')
])

# 编译模型
model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['acc'])

# 训练模型
history = model.fit(x_train, y_train, 
                    epochs=10,
                    batch_size=32,
                    validation_data=(x_val, y_val))

此时会提示“ValueError: Data cardinality is ambiguous: x sizes: 20 y sizes: 60 Make sure all arrays contain the same number of samples.”

正确示例：

import numpy as np
from tensorflow.keras.utils import to_categorical

# 生成数据
x_train = np.random.random((100, 20, 30))
y_train = np.random.randint(10, size=(100,))   
y_train = to_categorical(y_train)  # 将标签one-hot编码

x_val = np.random.random((50, 20, 30))
y_val = np.random.randint(10, size=(50,))  # 样本数相同
y_val = to_categorical(y_val)

# 构建模型
model = keras.models.Sequential([
    keras.layers.Flatten(input_shape=(20, 30)),
    keras.layers.Dense(128, activation='relu'),