模型中的Keras值误差。

Question

我正在尝试构建神经网络并在下面执行此操作：

from keras.layers import Dense, Activation

model.add(Dense(units=64))
model.add(Activation('relu'))
model.add(Dense(units=10))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
              optimizer='sgd',
              metrics=['accuracy'])

我将x_train和y_train指定为numpy数组：

x_train=np.asarray(X_train)
y_train=np.asarray(y_train)
x_train.shape #(261, 8)
y_train.shape #(261,)

model.compile(optimizer='rmsprop',
              loss='categorical_crossentropy',
              metrics=['accuracy'])
model.fit(x_train, y_train, epochs=5, batch_size=32)

在输出时我有一个错误：

ValueError: Error when checking input: expected dense_1_input to have shape (None, 100) but got array with shape (261, 8)

我做错了什么？