Keras (tensorflow后端)获取"TypeError: unhashable type：'Dimension'“

Question

嗨，我在拟合这个模型时遇到了一个尺寸错误，有人知道为什么吗？

num_classes = 11
input_shape = (64,64,1)
batch_size = 128
epochs = 12
X_train = tf.reshape(X_train, [-1, 64, 64, 1])
X_test = tf.reshape(X_test, [-1, 64, 64, 1])

model = Sequential()
model.add(Conv2D(32, kernel_size=(3,3), strides=1, activation='relu', input_shape=input_shape)) 
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,
          optimizer=keras.optimizers.Adadelta(),
          metrics=['accuracy'])

model.fit(X_train, y_train,
      batch_size=batch_size,
      epochs=epochs,
      verbose=1,
      validation_data=(X_test, y_test))

每个变量的维度为

X_train = (27367, 64, 64, 1)
X_test = (4553, 64, 64, 1)
y_train = (164202, 11)
y_test = (27318, 11)

Answer 1

这是因为您使用的是tf.reshape，它返回一个张量，而Keras模型的fit方法不能很好地处理张量。

考虑使用np.reshape，它将做完全相同的事情。