问题描述
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:
h5py._objects.with_phil.wrapper中第54行的文件“ h5py_objects.pyx”
在h5py._objects.with_phil.wrapper中的文件“ h5py_objects.pyx”(第55行)
在h5py.h5o.link中的文件“ h5py \ h5o.pyx”,第202行,
OSError:无法创建链接(名称已存在)
- 我试图排除此处提到的优化器:https://github.com/tensorflow/tensorflow/issues/27688。
- 我尝试过TensorFlow的不同版本,例如2.2和2.3。
- 我尝试重新安装h5py,如此处提到的:RuntimeError: Unable to create link (name already exists) when I append hdf5 file?。
一切都没有成功!
以下是模型的相关代码:
(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')
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,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,batch_size=batch_size)
__buildFeatureColums(feature_columns,data,bucketSizeGEO,True)
print("preprocessing completed")
return (feature_columns,test_ds)
def __buildFeatureColums(feature_columns,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))
功能已重新嵌入到嵌入中:
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',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',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
解决方法
以h5格式保存模型时,错误OSError: Unable to create link (name already exists)
是由某些重复的变量名称引起的。通过for i,w in enumerate(model.weights): print(i,w.name)
进行的检查显示,它们是embedding_weights名称。
通常,在构建feature_column
时,传递到每个功能列的独特key
将用于构建独特变量name
。在TF 2.1中可以正常使用,但在TF 2.2和2.3中可以使用,而应该是fixed in TF 2.4 nigthly。
我对 TF 2.3 的解决方法基于 @SajanGohil 的评论,但我的问题是 weight 名称(不是 layer 名称):
for i in range(len(model.weights)):
model.weights[i]._handle_name = model.weights[i].name + "_" + str(i)
同样的警告也适用:这种方法会操纵 TF 内部结构,因此不是面向未来的。