警告：tensorflow：不推荐使用create_partitioned_variables

Question

我收到此WARNING

  

警告：tensorflow：不推荐使用create_partitioned_variables。将tf.get_variable与分区器集或tf.get_partitioned_variable_list一起使用。

我没有使用函数create_partitioned_variables

我正在使用tensorflow.__version__ 0.9.0

解决此问题的最合适方法是什么WARNING

如果你和pandas / numpy一起安装了tensorflow，你应该可以复制并粘贴这段代码。

设置

import pandas as pd
import numpy as np
import tensorflow as tf
import tempfile

np.random.seed([3,1415])
df = pd.DataFrame(dict(cat1=np.random.choice(('Yes', 'No'), (100,),),
                       val1=np.random.rand(100),
                       val2=np.random.rand(100),
                       val3=np.random.rand(100),
                       label=np.random.choice((0, 1), (100,))))

LABEL_COLUMN = "label"

trainBegin, trainEnd = 0, 80
testBegin, testEnd = 80, 100
df_train = df.iloc[trainBegin:trainEnd, :]
df_test = df.iloc[testBegin:testEnd, :]

CONTINUOUS_COLUMNS = ['val1', 'val2', 'val3']
CATEGORICAL_COLUMNS = ['cat1']

def input_fn(df):
    # Creates a dictionary mapping from each continuous feature column name (k) to
    # the values of that column stored in a constant Tensor.
    continuous_cols = {k: tf.constant(df[k].values)
                       for k in CONTINUOUS_COLUMNS}
    # Creates a dictionary mapping from each categorical feature column name (k)
    # to the values of that column stored in a tf.SparseTensor.
    categorical_cols = {k: tf.SparseTensor(
            indices=[[i, 0] for i in range(df[k].size)],
            values=df[k].values,
            shape=[df[k].size, 1])
                        for k in CATEGORICAL_COLUMNS}
    # Merges the two dictionaries into one.
    feature_cols = dict(continuous_cols.items() + categorical_cols.items())
    # Converts the label column into a constant Tensor.
    label = tf.constant(df[LABEL_COLUMN].values)
    # Returns the feature columns and the label.
    return feature_cols, label

def train_input_fn():
    return input_fn(df_train)

def eval_input_fn():
    return input_fn(df_test)

val1 = tf.contrib.layers.real_valued_column("val1")
val2 = tf.contrib.layers.real_valued_column("val2")
val3 = tf.contrib.layers.real_valued_column("val3")

cat1 = tf.contrib.layers.sparse_column_with_keys(column_name="cat1", keys=["Yes", "No"])

wide_columns = [val1, val2, val3, cat1] 

当我跑步时，

WARNINGS来了：

model_dir = tempfile.mkdtemp()
m = tf.contrib.learn.LinearClassifier(feature_columns=wide_columns, model_dir=model_dir)

m.fit(input_fn=train_input_fn, steps=200)

results = m.evaluate(input_fn=eval_input_fn, steps=1)
for key in sorted(results):
    print("%s: %s" % (key, results[key]))

如果我改为运行：

model_dir = tempfile.mkdtemp()
m = tf.contrib.learn.LinearClassifier(feature_columns=wide_columns[:-1], model_dir=model_dir)
# removing last feature columns which is categorical using [:-1]  ^^^^^

m.fit(input_fn=train_input_fn, steps=200)

results = m.evaluate(input_fn=eval_input_fn, steps=1)
for key in sorted(results):
    print("%s: %s" % (key, results[key]))

我没有错误。

accuracy: 0.45
eval_auc: 0.459596
loss: 0.771354

结论

我将其缩小为使用.sparse_column_with_keys创建的分类功能，但我应该怎么做呢？

Answer 1

基本上sparse_column_with_keys正在使用create_partitioned_variables()进行初始化，但是，在create_partitioned_variables()类中，它们会发出警告，基本上说create_partitioned_variables()不是可接受的方式再创建分区变量相反，您可以使用get_variable()功能。

如果您转到tensorflow/contrib/layers/python/layers并打开_feature_column.py_，您会发现sparse_column_with_keys的嵌入使用create_partitioned_variables()。要解决此问题，请导入get_variable function（from tensorflow.python.ops.variable_scope import get_variable），然后使用embeddings而不是{定义变量create_partitioned_variables()（最初应使用get_variable()） {1}}。我不认为警告真的很重要。