TensorFlow 2.x：无法以h5格式保存经过训练的模型（OSError：无法创建链接（名称已经存在））

我的模型使用预处理的数据来预测客户是私人客户还是非私人客户。预处理步骤使用诸如feature_column.bucketized_column（…），feature_column.embedding_column（…）等步骤。训练后，我试图保存模型，但出现以下错误：

在h5py._objects.with_phil.wrapper中的文件“ h5py_objects.pyx”，第54行，在h5py._objects.with_phil.wrapper中的
文件“ h5py_objects.pyx”，第55行，在h5py中的
文件“ h5py \ h5o.pyx”，第202行.h5o.link
OSError：无法创建链接（名称已存在）

我尝试了以下方法来解决我的问题：

• 我试图排除此处提到的优化器：https : //github.com/tensorflow/tensorflow/issues/27688。
• 我尝试了2.2和2.3等不同版本的TensorFlow。
• 我尝试重新安装h5py，如此处所述：RuntimeError：当我附加hdf5文件时，无法创建链接（名称已经存在）吗？。

一切都没有成功！

这是模型的相关代码：

(feature_columns, train_ds, val_ds, test_ds) = preprocessing.getPreProcessedDatasets(args.data, args.zip, args.batchSize)

feature_layer = tf.keras.layers.DenseFeatures(feature_columns, trainable=False)

model = tf.keras.models.Sequential([
        feature_layer,
        tf.keras.layers.Dense(1, activation=tf.nn.sigmoid)
    ])

model.compile(optimizer='sgd',
        loss='binary_crossentropy',
        metrics=['accuracy'])

paramString = "Arg-e{}-b{}-z{}".format(args.epoch, args.batchSize, bucketSizeGEO)

...

model.fit(train_ds,
              validation_data=val_ds,
              epochs=args.epoch,
              callbacks=[tensorboard_callback])


model.summary()

loss, accuracy = model.evaluate(test_ds)
print("Accuracy", accuracy)

paramString = paramString + "-a{:.4f}".format(accuracy)

outputName = "logReg" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S") + paramStrin

if args.saveModel:
       filepath = "./saved_models/" + outputName + ".h5"
       model.save(filepath, save_format='h5')

在预处理模块中调用的函数：

def getPreProcessedDatasets(filepath, zippath, batch_size, bucketSizeGEO):
    print("start preprocessing...")

    path = filepath
    data = pd.read_csv(path, dtype={
    "NAME1": np.str_, 
    "NAME2": np.str_, 
    "EMAIL1": np.str_, 
    "ZIP": np.str_, 
    "STREET": np.str_, 
    "LONGITUDE":np.floating, 
    "LATITUDE": np.floating, 
    "RECEIVERTYPE": np.int64}) 

    feature_columns = []

    data = data.fillna("NaN")

    data = __preProcessName(data)
    data = __preProcessStreet(data)
    
    train, test = train_test_split(data, test_size=0.2, random_state=0)
    train, val = train_test_split(train, test_size=0.2, random_state=0)

    train_ds = __df_to_dataset(train, batch_size=batch_size)
    val_ds = __df_to_dataset(val, shuffle=False, batch_size=batch_size)
    test_ds = __df_to_dataset(test, shuffle=False, batch_size=batch_size)


    __buildFeatureColums(feature_columns, data, zippath, bucketSizeGEO, True)

    print("preprocessing completed")

    return (feature_columns, train_ds, val_ds, test_ds)

调用功能的不同预处理功能：

def __buildFeatureColums(feature_columns, data, zippath, bucketSizeGEO, addCrossedFeatures):
    
    feature_columns.append(__getFutureColumnLon(bucketSizeGEO))
    feature_columns.append(__getFutureColumnLat(bucketSizeGEO))
    
    (namew1_one_hot, namew2_one_hot) = __getFutureColumnsName(__getNumberOfWords(data, 'NAME1PRO'))
    feature_columns.append(namew1_one_hot)
    feature_columns.append(namew2_one_hot)
    
    feature_columns.append(__getFutureColumnStreet(__getNumberOfWords(data, 'STREETPRO')))
    
    feature_columns.append(__getFutureColumnZIP(2223, zippath))
    
    if addCrossedFeatures:
        feature_columns.append(__getFutureColumnCrossedNames(100))
        feature_columns.append(__getFutureColumnCrossedZIPStreet(100, 2223, zippath))

函数重新嵌入：

def __getFutureColumnsName(name_num_words):
    vocabulary_list = np.arange(0, name_num_words + 1, 1).tolist()

    namew1_voc = tf.feature_column.categorical_column_with_vocabulary_list(
        key='NAME1W1', vocabulary_list=vocabulary_list, dtype=tf.dtypes.int64)
    namew2_voc = tf.feature_column.categorical_column_with_vocabulary_list(
        key='NAME1W2', vocabulary_list=vocabulary_list, dtype=tf.dtypes.int64)

    dim = __getNumberOfDimensions(name_num_words)

    namew1_embedding = feature_column.embedding_column(namew1_voc, dimension=dim)
    namew2_embedding = feature_column.embedding_column(namew2_voc, dimension=dim)

    return (namew1_embedding, namew2_embedding)

def __getFutureColumnStreet(street_num_words):
    vocabulary_list = np.arange(0, street_num_words + 1, 1).tolist()

    street_voc = tf.feature_column.categorical_column_with_vocabulary_list(
        key='STREETW', vocabulary_list=vocabulary_list, dtype=tf.dtypes.int64)

    dim = __getNumberOfDimensions(street_num_words)

    street_embedding = feature_column.embedding_column(street_voc, dimension=dim)

    return street_embedding

def __getFutureColumnZIP(zip_num_words, zippath):
    zip_voc = feature_column.categorical_column_with_vocabulary_file(
    key='ZIP', vocabulary_file=zippath, vocabulary_size=zip_num_words,
    default_value=0)

    dim = __getNumberOfDimensions(zip_num_words)

    zip_embedding = feature_column.embedding_column(zip_voc, dimension=dim)

    return zip_embedding