Keras 2.14 中的优化器格式发生变化,导致简单模型无法导入

嘿大家, 我在加载简单的 Python keras 模型时遇到了问题。Python keras 模型: `model = keras.Sequential([ keras.layers.Dense(32, activation='relu', input_shape=(132,)), keras.layers.Dropout(.2), keras.layers.Dense(16, activation='relu'), keras.layers.Dense(41, activation='softmax') ]) optimizer = SGD(learning_rate=0.1) model.compile(optimizer=optimizer, loss=keras.losses.sparse_categorical_crossentropy, metrics=['accuracy'])

model.fit(train_x, train_y, epochs=10, batch_size=32, validation_split=0.1)

test_loss, test_accuracy = model.evaluate(test_x, test_y)
print(f"Test accuracy: {test_accuracy}")

model.save("test_model.h5")`

Java 代码出现错误: MultiLayerNetwork model = KerasModelImport.importKerasSequentialModelAndWeights("path/to/model.h5");

错误本身: org.deeplearning4j.nn.modelimport.keras.exceptions.UnsupportedKerasConfigurationException 错误消息: 具有名称 Custom>SGD的优化器无法与 DL4J 优化器匹配。请注意,自定义 TFOptimizers 不受模型导入支持。