Python 使用tf估计器导出模型并导出保存的模型函数
我正在做一个基于Tensorflow的深度神经网络回归。当我试图用tf.estimator保存模型时,我得到以下错误:Python 使用tf估计器导出模型并导出保存的模型函数,python,machine-learning,tensorflow,neural-network,google-cloud-ml-engine,Python,Machine Learning,Tensorflow,Neural Network,Google Cloud Ml Engine,我正在做一个基于Tensorflow的深度神经网络回归。当我试图用tf.estimator保存模型时,我得到以下错误: raise ValueError('Feature {} is not in features dictionary.'.format(key)) ValueError: Feature ad_provider is not in features dictionary. 我需要将其导出,以便在谷歌云平台中部署支持预测的模型。 下面是我定义列的位置: CSV_COLUMN
raise ValueError('Feature {} is not in features dictionary.'.format(key))
ValueError: Feature ad_provider is not in features dictionary.
我需要将其导出,以便在谷歌云平台中部署支持预测的模型。
下面是我定义列的位置:
CSV_COLUMNS = [
"ad_provider", "device", "split_group","gold", "secret_areas",
"scored_enemies", "tutorial_sec", "video_success"
]
FEATURES = ["ad_provider", "device", "split_group","gold", "secret_areas",
"scored_enemies", "tutorial_sec"]
LABEL = "video_success"
ad_provider = tf.feature_column.categorical_column_with_vocabulary_list(
"ad_provider", ["Organic","Apple Search Ads","googleadwords_int",
"Facebook Ads","website"] )
split_group = tf.feature_column.categorical_column_with_vocabulary_list(
"split_group", [1,2,3,4])
device = tf.feature_column.categorical_column_with_hash_bucket(
"device", hash_bucket_size=100)
secret_areas = tf.feature_column.numeric_column("secret_areas")
gold = tf.feature_column.numeric_column("gold")
scored_enemies = tf.feature_column.numeric_column("scored_enemies")
finish_tutorial_sec = tf.feature_column.numeric_column("tutorial_sec")
video_success = tf.feature_column.numeric_column("video_success")
feature_columns = [
tf.feature_column.indicator_column(ad_provider),
tf.feature_column.embedding_column(device, dimension=8),
tf.feature_column.indicator_column(split_group),
tf.feature_column.numeric_column(key="gold"),
tf.feature_column.numeric_column(key="secret_areas"),
tf.feature_column.numeric_column(key="scored_enemies"),
tf.feature_column.numeric_column(key="tutorial_sec"),
]
之后,我创建一个函数以在JSON字典中导出我的模型。我不确定我的发球功能是否做得很好
def json_serving_input_fn():
"""Build the serving inputs."""
inputs = {}
for feat in feature_columns:
inputs[feat.name] = tf.placeholder(shape=[None], dtype= feat.dtype if
hasattr(feat, 'dtype') else tf.string)
features = {
key: tf.expand_dims(tensor, -1)
for key, tensor in inputs.items()
}
return tf.contrib.learn.InputFnOps(features, None, inputs)
以下是我的代码的其余部分:
def main(unused_argv):
#Normalize columns 'Gold' and 'tutorial_sec' for Traininig Set
train_n = training_set
train_n['gold'] = (train_n['gold'] - train_n['gold'].mean()) / (train_n['gold'].max() - train_n['gold'].min())
train_n['tutorial_sec'] = (train_n['tutorial_sec'] - train_n['tutorial_sec'].mean()) / (train_n['tutorial_sec'].max() - train_n['tutorial_sec'].min())
train_n['scored_enemies'] = (train_n['scored_enemies'] - train_n['scored_enemies'].mean()) / (train_n['scored_enemies'].max() - train_n['scored_enemies'].min())
test_n = test_set
test_n['gold'] = (test_n['gold'] - test_n['gold'].mean()) / (test_n['gold'].max() - test_n['gold'].min())
test_n['tutorial_sec'] = (test_n['tutorial_sec'] - test_n['tutorial_sec'].mean()) / (test_n['tutorial_sec'].max() - test_n['tutorial_sec'].min())
test_n['scored_enemies'] = (test_n['scored_enemies'] - test_n['scored_enemies'].mean()) / (test_n['scored_enemies'].max() - test_n['scored_enemies'].min())
train_input_fn = tf.estimator.inputs.pandas_input_fn(
x=train_n,
y=pd.Series(train_n[LABEL].values),
batch_size=100,
num_epochs=None,
shuffle=True)
test_input_fn = tf.estimator.inputs.pandas_input_fn(
x=test_n,
y=pd.Series(test_n[LABEL].values),
batch_size=100,
num_epochs=1,
shuffle=False)
regressor = tf.estimator.DNNRegressor(feature_columns=feature_columns,
hidden_units=[40, 30, 20],
model_dir="model1",
optimizer='RMSProp'
)
# Train
regressor.train(input_fn=train_input_fn, steps=5)
regressor.export_savedmodel("test",json_serving_input_fn)
#Evaluate loss over one epoch of test_set.
#For each step, calls `input_fn`, which returns one batch of data.
ev = regressor.evaluate(
input_fn=test_input_fn)
loss_score = ev["loss"]
print("Loss: {0:f}".format(loss_score))
for key in sorted(ev):
print("%s: %s" % (key, ev[key]))
# Print out predictions over a slice of prediction_set.
y = regressor.predict(
input_fn=test_input_fn)
# Array with prediction list!
predictions = list(p["predictions"] for p in y)
#real = list(p["real"] for p in pd.Series(training_set[LABEL].values))
real = test_set[LABEL].values
diff = np.subtract(real,predictions)
diff = np.absolute(diff)
diff = np.mean(diff)
print("Mean Square Error of Test Set = ",diff*diff)
除了您提到的问题外,我预计您还会遇到多个其他问题:
- 您正在使用TensorFlow 1.3中引入的
。CloudML引擎仅正式支持TF1.2tf.estimator.DnnRegressor
- 您正在规范化panda数据帧中的功能,而这不会在服务时发生(除非您在客户端这样做)。这会引入倾斜,您将得到较差的预测结果
tf.contrib.learn.DNNRegressor
,它只需要稍作修改:
regressor = tf.estimator.DNNRegressor(
feature_columns=feature_columns,
hidden_units=[40, 30, 20],
model_dir="model1",
optimizer='RMSProp'
)
regressor.fit(input_fn=train_input_fn, steps=5)
regressor.export_savedmodel("test",json_serving_input_fn)
注意fit
而不是train
(NB:您的json\u服务\u输入fn
实际上已经为TF 1.2编写,并且与TF 1.3不兼容。这对现在来说是好的)
现在,您看到的错误的根本原因是列/功能ad\u provider
不在输入和功能列表中(但您确实有ad\u provider\u指示器
)。这是因为您正在迭代feature\u列
,而不是通过原始输入列列表。解决这一问题的方法是迭代实际输入,而不是特征列;但是,我们还需要知道类型(只需几列即可简化):
最后,要规范化数据,您可能需要在图形中这样做。您可以尝试使用,或者编写一个自定义估计器来进行转换,委托实际的模型实现DNNRegrestor。除了您提到的问题之外,我预计您还会遇到多个实际的其他问题:
- 您正在使用TensorFlow 1.3中引入的
。CloudML引擎仅正式支持TF1.2tf.estimator.DnnRegressor
- 您正在规范化panda数据帧中的功能,而这不会在服务时发生(除非您在客户端这样做)。这会引入倾斜,您将得到较差的预测结果
tf.contrib.learn.DNNRegressor
,它只需要稍作修改:
regressor = tf.estimator.DNNRegressor(
feature_columns=feature_columns,
hidden_units=[40, 30, 20],
model_dir="model1",
optimizer='RMSProp'
)
regressor.fit(input_fn=train_input_fn, steps=5)
regressor.export_savedmodel("test",json_serving_input_fn)
注意fit
而不是train
(NB:您的json\u服务\u输入fn
实际上已经为TF 1.2编写,并且与TF 1.3不兼容。这对现在来说是好的)
现在,您看到的错误的根本原因是列/功能ad\u provider
不在输入和功能列表中(但您确实有ad\u provider\u指示器
)。这是因为您正在迭代feature\u列
,而不是通过原始输入列列表。解决这一问题的方法是迭代实际输入,而不是特征列;但是,我们还需要知道类型(只需几列即可简化):
最后,要规范化数据,您可能需要在图形中这样做。您可以尝试使用,或者编写一个自定义估计器来进行转换,委托实际的模型实现DNNRegrestor。我做了另一个答案来详细解释我的问题。我做了另一个答案来详细解释我的问题。