如何在运行神经网络时更改python程序以消除nan损失

如何更改我的神经网络多类分类不平衡数据集程序，以消除丢失的nan错误

encoder = LabelEncoder()
encoder.fit(y_train)
encoded_Yone = encoder.transform(y_train)
# convert integers to dummy variables (i.e. one hot encoded)
dummy_yone = np_utils.to_categorical(encoded_Yone)
#encode our testing set
encoder = LabelEncoder()
encoder.fit(y_test)
encoded_Ytwo = encoder.transform(y_test)
# convert integers to dummy variables (i.e. one hot encoded)
dummy_ytwo = np_utils.to_categorical(encoded_Ytwo)


model = Sequential()
 model.add(Dense(64, activation='relu', input_dim=78 ))
 model.add(Dropout(0.5))
 model.add(Dense(64, activation='relu'))
 model.add(Dropout(0.5))
 model.add(Dense(15, activation='softmax'))

 adam = keras.optimizers.Adam(lr=0.001)

 model.compile(loss='categorical_crossentropy',
     optimizer=adam,
     metrics=['accuracy'])

 model.fit(x_train, dummy_yone,
     epochs=10000,
     batch_size=128,
          verbose=2,
          validation_split=0.2)

错误：

---

如果没有关键信息，您的问题很难回答。请提供有关您的输入和输入形状的更多信息。Read：你确信你的<代码> DuMyYyYON[/COD]遵循<代码>（DimyyyyOn.SoM（轴＝-1）＝1）吗？