Keras 中的 load_model 和 Lambda 层

如何加载具有 lambda 层的模型？

这是重现行为的代码：

MEAN_LANDMARKS = np.load('data/mean_shape_68.npy')

def add_mean_landmarks(x):
    mean_landmarks = np.array(MEAN_LANDMARKS, np.float32)
    mean_landmarks = mean_landmarks.flatten()
    mean_landmarks_tf = tf.convert_to_tensor(mean_landmarks)
    x = x + mean_landmarks_tf
    return x

def get_model():
    inputs = Input(shape=(8, 128, 128, 3))
    cnn = VGG16(include_top=False, weights='imagenet', input_shape=(128, 128, 3))
    x = TimeDistributed(cnn)(inputs)
    x = TimeDistributed(Flatten())(x)
    x = LSTM(256)(x)
    x = Dense(68 * 2, activation='linear')(x)

    x = Lambda(add_mean_landmarks)(x)

    model = Model(inputs=inputs, outputs=x)
    optimizer = Adadelta()
    model.compile(optimizer=optimizer, loss='mae')

    return model

模型编译后我可以保存它，但是当我尝试使用以下命令加载它时load_model函数我收到错误：

in add_mean_landmarks
    mean_landmarks = np.array(MEAN_LANDMARKS, np.float32)
NameError: name 'MEAN_LANDMARKS' is not defined

据我了解MEAN_LANDMARKS不作为常数张量并入图中。这也与这个问题有关：如何在 Keras 中添加常量张量？ https://stackoverflow.com/questions/52831235/how-to-add-constant-tensor-in-keras/52831446#comment92584381_52831446

你需要通过custom_objects论证load_model功能：

model = load_model('model_file_name.h5', custom_objects={'MEAN_LANDMARKS': MEAN_LANDMARKS})

在 Keras 文档中查找更多信息：处理保存模型中的自定义图层（或其他自定义对象） https://keras.io/getting-started/faq/#handling-custom-layers-or-other-custom-objects-in-saved-models.