每當我運行這段代碼時，Python 都會停止工作。為了確保這不是我系統的問題，我嘗試在 Google Colab 中運行它，但它也崩潰了。當執行到達model.fit行時發生崩潰data = load_iris()X = data['data']y = data['target']X_train, X_test, y_train, y_test = train_test_split(X,y, test_size = 0.33, random_state =23)def energy(x):    val,vec = tf.linalg.eigh(x)    en = tf.reduce_sum(tf.math.square(val))    return endef energy_loss(y_actual,y_predicted):    mtm_actual = tf.linalg.matmul(y_actual,tf.transpose(y_actual))    ptp_actual = tf.linalg.matmul(y_predicted,tf.transpose(y_predicted))    actual_energy = energy(y_actual)    predicted_energy = energy(y_predicted)    return tf.math.abs(actual_energy - predicted_energy)model = Sequential()model.add(Dense(32,input_dim=4))model.add(Dense(64,activation='relu'))model.add(Dense(128,activation='relu'))model.add(Dense(64,activation='relu'))model.add(Dense(3,activation='relu'))opt = Adam(lr = 1)model.compile(optimizer = opt, loss=energy_loss,metrics=['accuracy'])model.fit(X_train,X_train,epochs=25,verbose = 1,batch_size = 5)運行此代碼時，我使用的是 tensorflow 1.15.0。任何想法是什么導致了這個問題？