在Keras模型上进行特征工程预处理的Tensorflow 2文档似乎很混乱,不是很友好。
目前我有一个简单的Keras N层模型,TF特征列作为致密层进给。对于训练,我有CSV文件,使用 tf.dataset
API,我已经写了一个功能工程函数,它使用 dataset.map
函数。
def feature_engg_features(features):
#Add new features
features['nodlgrbyvpatd'] = features['NODLGR'] / features['VPATD']
return(features)
我可以使用 tf.keras.models.save_model
的方法。然而,我不知道如何连接上 feature_engineering
服务功能的步骤。
要求: 现在,我想把上述相同的功能工程功能附加到我的 serving function
因此,在JSON输入中通过 tensorflow_model_server
同样的功能工程步骤被应用。我知道Keras中的lambda Layer选项,但我想通过 saved_model
方法,但这里有很多困难。
例如,下面的代码给出了错误。
def feature_engg_features(features):
#Add new features
features['nodlgrbyvpatd'] = features['NODLGR'] / features['VPATD']
return(features)
@tf.function
def serving(data):
data = tf.map_fn(feature_engg_features, data, dtype=tf.float32)
# Predict
predictions = m_(data)
version = "1"
tf.keras.models.save_model(
m_,
"./exported_model/" + version,
overwrite=True,
include_optimizer=True,
save_format=None,
signatures=serving,
options=None
)
错误,我没有提供Keras模型的InputSignature。
Only `tf.functions` with an input signature or concrete functions can be used as a signature.
上面的错误是因为我没有提供Keras模型的InputSignature,但是我无法理解我有13个输入字段,什么是预期的输入签名。
所以我想知道是否有谁知道解决这个问题的最简单方法。这是一个非常基本的要求,而Tensorflow似乎把这个问题复杂化了,让Keras Tensorflow模型服务变得非常复杂。
EDIT:我修好了,所以必须为每个特征生成并传递TensorSpec,而且还必须在服务函数中调用model( )。
@tf.function
def serving(WERKS, DIFGRIRD, SCENARIO, TOTIRQTY, VSTATU, EKGRP, TOTGRQTY, VPATD, EKORG, NODLGR, DIFGRIRV, NODLIR, KTOKK):
##Feature engineering
nodlgrbyvpatd = tf.cast(NODLGR / VPATD, tf.float32)
payload = {
'WERKS': WERKS,
'DIFGRIRD': DIFGRIRD,
'SCENARIO': SCENARIO,
'TOTIRQTY': TOTIRQTY,
'VSTATU': VSTATU,
'EKGRP': EKGRP,
'TOTGRQTY': TOTGRQTY,
'VPATD': VPATD,
'EKORG': EKORG,
'NODLGR': NODLGR,
'DIFGRIRV': DIFGRIRV,
'NODLIR': NODLIR,
'KTOKK': KTOKK,
'nodlgrbyvpatd': nodlgrbyvpatd,
}
## Predict
##IF THERE IS AN ERROR IN NUMBER OF PARAMS PASSED HERE OR DATA TYPE THEN IT GIVES ERROR, "COULDN'T COMPUTE OUTPUT TENSOR"
predictions = m_(payload)
return predictions
serving = serving.get_concrete_function(WERKS=tf.TensorSpec([None,], dtype= tf.string, name='WERKS'),
DIFGRIRD=tf.TensorSpec([None,], name='DIFGRIRD'),
SCENARIO=tf.TensorSpec([None,], dtype= tf.string, name='SCENARIO'),
TOTIRQTY=tf.TensorSpec([None,], name='TOTIRQTY'),
VSTATU=tf.TensorSpec([None,], dtype= tf.string, name='VSTATU'),
EKGRP=tf.TensorSpec([None,], dtype= tf.string, name='EKGRP'),
TOTGRQTY=tf.TensorSpec([None,], name='TOTGRQTY'),
VPATD=tf.TensorSpec([None,], name='VPATD'),
EKORG=tf.TensorSpec([None,], dtype= tf.string, name='EKORG'),
NODLGR=tf.TensorSpec([None,], name='NODLGR'),
DIFGRIRV=tf.TensorSpec([None,], name='DIFGRIRV'),
NODLIR=tf.TensorSpec([None,], name='NODLIR'),
KTOKK=tf.TensorSpec([None,], dtype= tf.string, name='KTOKK')
)
version = "1"
tf.saved_model.save(
m_,
"./exported_model/" + version,
signatures=serving
)
所以正确的方法在这里,特征工程和预处理可以在 serving_default
方法通过下面的选项。我通过Tensorflow serving进一步测试。
@tf.function
def serving(WERKS, DIFGRIRD, SCENARIO, TOTIRQTY, VSTATU, EKGRP, TOTGRQTY, VPATD, EKORG, NODLGR, DIFGRIRV, NODLIR, KTOKK):
##Feature engineering
nodlgrbyvpatd = tf.cast(NODLGR / VPATD, tf.float32)
payload = {
'WERKS': WERKS,
'DIFGRIRD': DIFGRIRD,
'SCENARIO': SCENARIO,
'TOTIRQTY': TOTIRQTY,
'VSTATU': VSTATU,
'EKGRP': EKGRP,
'TOTGRQTY': TOTGRQTY,
'VPATD': VPATD,
'EKORG': EKORG,
'NODLGR': NODLGR,
'DIFGRIRV': DIFGRIRV,
'NODLIR': NODLIR,
'KTOKK': KTOKK,
'nodlgrbyvpatd': nodlgrbyvpatd,
}
## Predict
##IF THERE IS AN ERROR IN NUMBER OF PARAMS PASSED HERE OR DATA TYPE THEN IT GIVES ERROR, "COULDN'T COMPUTE OUTPUT TENSOR"
predictions = m_(payload)
return predictions
serving = serving.get_concrete_function(WERKS=tf.TensorSpec([None,], dtype= tf.string, name='WERKS'),
DIFGRIRD=tf.TensorSpec([None,], name='DIFGRIRD'),
SCENARIO=tf.TensorSpec([None,], dtype= tf.string, name='SCENARIO'),
TOTIRQTY=tf.TensorSpec([None,], name='TOTIRQTY'),
VSTATU=tf.TensorSpec([None,], dtype= tf.string, name='VSTATU'),
EKGRP=tf.TensorSpec([None,], dtype= tf.string, name='EKGRP'),
TOTGRQTY=tf.TensorSpec([None,], name='TOTGRQTY'),
VPATD=tf.TensorSpec([None,], name='VPATD'),
EKORG=tf.TensorSpec([None,], dtype= tf.string, name='EKORG'),
NODLGR=tf.TensorSpec([None,], name='NODLGR'),
DIFGRIRV=tf.TensorSpec([None,], name='DIFGRIRV'),
NODLIR=tf.TensorSpec([None,], name='NODLIR'),
KTOKK=tf.TensorSpec([None,], dtype= tf.string, name='KTOKK')
)
version = "1"
tf.saved_model.save(
m_,
"./exported_model/" + version,
signatures=serving
)