Tensorflow:不支持的可调用

Question

我试着在tensorflow网站上学习教程https://www.tensorflow.org/tutorials/estimator/linear

这是一个使用线性回归的代码，但由于指定的错误，我无法做到这一点，我无法理解

但我得到了一个不支持的可调用错误

这是代码

import os
import sys
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from IPython.display import clear_output
from six.moves import urllib
import tensorflow.compat.v2.feature_column as fc
import tensorflow as tf
dftrain = pd.read_csv('https://storage.googleapis.com/tf-datasets/titanic/train.csv')
dfeval = pd.read_csv('https://storage.googleapis.com/tf-datasets/titanic/eval.csv')
y_train = dftrain.pop('survived')
y_eval = dfeval.pop('survived')
CATEGORICAL_COLUMNS = ['sex', 'n_siblings_spouses', 'parch', 'class', 'deck', 'embark_town', 'alone']
NUMERIC_COLUMNS = ['age', 'fare']
feature_columns = []
for feature_name in CATEGORICAL_COLUMNS:
vocabulary = dftrain[feature_name].unique()
feature_columns.append(tf.feature_column.categorical_column_with_vocabulary_list(feature_name, vocabulary))
for feature_name in NUMERIC_COLUMNS:
feature_columns.append(tf.feature_column.numeric_column(feature_name, dtype=tf.float32))

def make_input_fn(data_df, label_df, num_epochs=20, shuffle=True, batch_size=32):
def input_function():
ds = tf.data.Dataset.from_tensor_slices((dict(data_df), label_df))
if shuffle:
ds = ds.shuffle(1000)
ds = ds.batch(batch_size).repeat(num_epochs)
return ds
return input_function()

train_input_fn = make_input_fn(dftrain, y_train)
eval_input_fn = make_input_fn(dfeval, y_eval, num_epochs=1, shuffle=False)
linear_est = tf.estimator.LinearClassifier(feature_columns=feature_columns)
linear_est.train(train_input_fn)
result = linear_est.evaluate(eval_input_fn)
clear_output()
print(result)

这就是我得到的错误

Traceback (most recent call last):
File "C:/Users/gotru/PycharmProjects/tensor/Linear_Regression.py", line 46, in <module>
linear_est.train(train_input_fn)
File "C:Usersgotruanaconda3envstensorflowlibsite-packagestensorflow_estimatorpythonestimatorestimator.py", line 374, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "C:Usersgotruanaconda3envstensorflowlibsite-packagestensorflow_estimatorpythonestimatorestimator.py", line 1164, in _train_model
return self._train_model_default(input_fn, hooks, saving_listeners)
File "C:Usersgotruanaconda3envstensorflowlibsite-packagestensorflow_estimatorpythonestimatorestimator.py", line 1191, in _train_model_default
input_fn, ModeKeys.TRAIN))
File "C:Usersgotruanaconda3envstensorflowlibsite-packagestensorflow_estimatorpythonestimatorestimator.py", line 1028, in _get_features_and_labels_from_input_fn
self._call_input_fn(input_fn, mode))
File "C:Usersgotruanaconda3envstensorflowlibsite-packagestensorflow_estimatorpythonestimatorestimator.py", line 1106, in _call_input_fn
input_fn_args = function_utils.fn_args(input_fn)
File "C:Usersgotruanaconda3envstensorflowlibsite-packagestensorflow_corepythonutilfunction_utils.py", line 57, in fn_args
args = tf_inspect.getfullargspec(fn).args
File "C:Usersgotruanaconda3envstensorflowlibsite-packagestensorflow_corepythonutiltf_inspect.py", line 257, in getfullargspec
return _getfullargspec(target)
File "C:Usersgotruanaconda3envstensorflowlibinspect.py", line 1132, in getfullargspec
raise TypeError('unsupported callable') from ex
TypeError: unsupported callable

提前感谢

Answer 1

下面的代码正在工作，没有任何错误

import os
import sys
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from IPython.display import clear_output
from six.moves import urllib
import tensorflow.compat.v2.feature_column as fc
import tensorflow as tf
# Load dataset.
dftrain = pd.read_csv('https://storage.googleapis.com/tf-datasets/titanic/train.csv')
dfeval = pd.read_csv('https://storage.googleapis.com/tf-datasets/titanic/eval.csv')
y_train = dftrain.pop('survived')
y_eval = dfeval.pop('survived')
CATEGORICAL_COLUMNS = ['sex', 'n_siblings_spouses', 'parch', 'class', 'deck',
'embark_town', 'alone']
NUMERIC_COLUMNS = ['age', 'fare']
feature_columns = []
for feature_name in CATEGORICAL_COLUMNS:
vocabulary = dftrain[feature_name].unique()
feature_columns.append(tf.feature_column.categorical_column_with_vocabulary_list(feature_name, vocabulary))
for feature_name in NUMERIC_COLUMNS:
feature_columns.append(tf.feature_column.numeric_column(feature_name, dtype=tf.float32))
def make_input_fn(data_df, label_df, num_epochs=10, shuffle=True, batch_size=32):
def input_function():
ds = tf.data.Dataset.from_tensor_slices((dict(data_df), label_df))
if shuffle:
ds = ds.shuffle(1000)
ds = ds.batch(batch_size).repeat(num_epochs)
return ds
return input_function
train_input_fn = make_input_fn(dftrain, y_train)
eval_input_fn = make_input_fn(dfeval, y_eval, num_epochs=1, shuffle=False)
#ds = make_input_fn(dftrain, y_train, batch_size=10)()
#for feature_batch, label_batch in ds.take(1):
#  print('Some feature keys:', list(feature_batch.keys()))
#  print()
#  print('A batch of class:', feature_batch['class'].numpy())
#  print()
#  print('A batch of Labels:', label_batch.numpy())
linear_est = tf.estimator.LinearClassifier(feature_columns=feature_columns)
linear_est.train(train_input_fn)
result = linear_est.evaluate(eval_input_fn)
clear_output()
print(result)

输出

{'accuracy': 0.75, 'accuracy_baseline': 0.625, 'auc': 0.83060914, 'auc_precision_recall': 0.78848886, 'average_loss': 0.5077252, 'label/mean': 0.375, 'loss': 0.5028537, 'precision': 0.6386555, 'prediction/mean': 0.46588355, 'recall': 0.7676768, 'global_step': 200}

Answer 2

我知道这已经一年了，但我想我无论如何都会回答。您的错误在make_input_fn中。最后，您调用return语句中的input_function。删除括号，以便返回函数本身。我犯了同样的错误：

将return input_function()更改为return input_function