python-3.x - 当我尝试创建 Kaggle 竞赛模型时获取 "Tensorflow %s is not valid scope name error"

Question

这是我的完整代码和回溯。这是我的机器学习模型的起始代码。将会有很多补充。

import pandas as pd
import tensorflow as tf
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn import metrics
from IPython import display
from tensorflow.python.data import Dataset
tf.logging.set_verbosity(tf.logging.ERROR)
pd.options.display.max_rows = 5
pd.options.display.float_format = '{:.1f}'.format

housing_data = pd.read_csv("train.csv")
housing_data = housing_data.reindex(
np.random.permutation(housing_data.index))
housing_data = pd.get_dummies(
housing_data).dropna()

预处理特征。这里还有更多工作要做。

def preprocess_features(housing_data):
    selected_features = housing_data
    selected_features = selected_features.drop(columns = "SalePrice")
    processed_features = selected_features.copy()
    return processed_features

def preprocess_target(housing_data):
    output_target = pd.DataFrame()
    output_target["SalePrice"] = (housing_data.SalePrice / 1000.0)
    return output_target

training_examples = preprocess_features(housing_data.head(900))
training_targets = preprocess_target(housing_data.head(900))

validation_examples = preprocess_features(housing_data.tail(221))
validation_targets = preprocess_target(housing_data.tail(221))

def construct_feature_columns(input_features):
    '''
    Returns the set of feature columns for tf.estimator classifiers and regressors
    '''
    return set([tf.feature_column.numeric_column(my_feature) for my_feature in input_features])


def my_input_fn(features, targets, batch_size = 1, shuffle = True, num_epochs = None):
    #convert the pandas dataframe into a numpy array

    features = {key:np.array(value) for key,value in dict(features).items()}

    #create the dataset
    ds = Dataset.from_tensor_slices((features,targets))
    ds = ds.batch(batch_size).repeat(num_epochs)

    #shuffle the data
    if shuffle:
        ds = ds.shuffle(1000)

    #return the features and targets tuple for next iteration
    features,labels= 
ds.make_one_shot_iterator().get_next()
    return features,labels

线性分类器

def train_linear_classifier_model(
    learning_rate,
    regularization_strength,
    steps,
    batch_size,
    training_examples,
    training_targets,
    validation_examples,
    validation_targets
):
    periods = 10
    steps_per_period = steps / periods

    my_optimizer = tf.train.FtrlOptimizer(learning_rate=learning_rate, l1_regularization_strength=regularization_strength)
    my_optimizer = tf.contrib.estimator.clip_gradients_by_norm(my_optimizer, 5.0)
    linear_classifier = tf.estimator.LinearClassifier(
      feature_columns=construct_feature_columns(training_examples),
      optimizer=my_optimizer
  )


    training_input_fn = lambda: my_input_fn(training_examples, 
                                          training_targets["SalePrice"], 
                                          batch_size=batch_size)
    predict_training_input_fn = lambda: my_input_fn(training_examples, 
                                                  training_targets["SalePrice"], 
                                                  num_epochs=1, 
                                                  shuffle=False)
    predict_validation_input_fn = lambda: my_input_fn(validation_examples, 
                                                    validation_targets["SalePrice"], 
                                                    num_epochs=1, 
                                                    shuffle=False)


    print("Training model...")
    print("LogLoss (on validation data):")
    training_log_losses = []
    validation_log_losses = []
    for period in range (0, periods):
        linear_classifier.train(
        input_fn=training_input_fn,
        steps=steps_per_period
    )
    # Take a break and compute predictions.
    training_probabilities = linear_classifier.predict(input_fn=predict_training_input_fn)
    training_probabilities = np.array([item['probabilities'] for item in training_probabilities])

    validation_probabilities = linear_classifier.predict(input_fn=predict_validation_input_fn)
    validation_probabilities = np.array([item['probabilities'] for item in validation_probabilities])

    # Compute training and validation loss.
    training_log_loss = metrics.log_loss(training_targets, training_probabilities)
    validation_log_loss = metrics.log_loss(validation_targets, validation_probabilities)
    # Occasionally print the current loss.
    print("  period %02d : %0.2f" % (period, validation_log_loss))
    # Add the loss metrics from this period to our list.
    training_log_losses.append(training_log_loss)
    validation_log_losses.append(validation_log_loss)
    print("Model training finished.")

  # Output a graph of loss metrics over periods.
    plt.ylabel("LogLoss")
    plt.xlabel("Periods")
    plt.title("LogLoss vs. Periods")
    plt.tight_layout()
    plt.plot(training_log_losses, label="training")
    plt.plot(validation_log_losses, label="validation")
    plt.legend()

    return linear_classifier

linear_classifier = train_linear_classifier_model(
    learning_rate=0.1,
    regularization_strength=0.1,
    steps=300,
    batch_size=100,
    training_examples=training_examples,
    training_targets=training_targets,
    validation_examples=validation_examples,
    validation_targets = validation_targets)

这是我的回溯

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-75-f9d203769761> in <module>()
      7     training_targets=training_targets,
      8     validation_examples=validation_examples,
----> 9     validation_targets = validation_targets)

<ipython-input-74-e1dbd56d9615> in train_linear_classifier_model(learning_rate, regularization_strength, steps, batch_size, training_examples, training_targets, validation_examples, validation_targets)
     40         linear_classifier.train(
     41         input_fn=training_input_fn,
---> 42         steps=steps_per_period
     43     )
     44     # Take a break and compute predictions.

c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\estimator\estimator.py in train(self, input_fn, hooks, steps, max_steps, saving_listeners)
    350 
    351     saving_listeners = _check_listeners_type(saving_listeners)
--> 352     loss = self._train_model(input_fn, hooks, saving_listeners)
    353     logging.info('Loss for final step: %s.', loss)
    354     return self

c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\estimator\estimator.py in _train_model(self, input_fn, hooks, saving_listeners)
    810       worker_hooks.extend(input_hooks)
    811       estimator_spec = self._call_model_fn(
--> 812           features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)
    813 
    814       if self._warm_start_settings:

c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\estimator\estimator.py in _call_model_fn(self, features, labels, mode, config)
    791 
    792     logging.info('Calling model_fn.')
--> 793     model_fn_results = self._model_fn(features=features, **kwargs)
    794     logging.info('Done calling model_fn.')
    795 

c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\estimator\canned\linear.py in _model_fn(features, labels, mode, config)
    314           optimizer=optimizer,
    315           partitioner=partitioner,
--> 316           config=config)
    317 
    318     super(LinearClassifier, self).__init__(

c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\estimator\canned\linear.py in _linear_model_fn(features, labels, mode, head, feature_columns, optimizer, partitioner, config)
    155     logit_fn = _linear_logit_fn_builder(
    156         units=head.logits_dimension, feature_columns=feature_columns)
--> 157     logits = logit_fn(features=features)
    158 
    159     def _train_op_fn(loss):

c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\estimator\canned\linear.py in linear_logit_fn(features)
     96         feature_columns=feature_columns,
     97         units=units,
---> 98         cols_to_vars=cols_to_vars)
     99     bias = cols_to_vars.pop('bias')
    100     if units > 1:

c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\feature_column\feature_column.py in linear_model(features, feature_columns, units, sparse_combiner, weight_collections, trainable, cols_to_vars)
    422     for column in sorted(feature_columns, key=lambda x: x.name):
    423       with variable_scope.variable_scope(
--> 424           None, default_name=column._var_scope_name):  # pylint: disable=protected-access
    425         ordered_columns.append(column)
    426         weighted_sum = _create_weighted_sum(

c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\ops\variable_scope.py in __enter__(self)
   1901 
   1902     try:
-> 1903       return self._enter_scope_uncached()
   1904     except:
   1905       if self._graph_context_manager is not None:

c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\ops\variable_scope.py in _enter_scope_uncached(self)
   2001           self._default_name)
   2002       try:
-> 2003         current_name_scope_name = current_name_scope.__enter__()
   2004       except:
   2005         current_name_scope.__exit__(*sys.exc_info())

c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\framework\ops.py in __enter__(self)
   5619       try:
   5620         self._name_scope = g.name_scope(self._name)
-> 5621         return self._name_scope.__enter__()
   5622       except:
   5623         self._g_manager.__exit__(*sys.exc_info())

c:\users\user\appdata\local\programs\python\python35\lib\contextlib.py in __enter__(self)
     57     def __enter__(self):
     58         try:
---> 59             return next(self.gen)
     60         except StopIteration:
     61             raise RuntimeError("generator didn't yield") from None

c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\framework\ops.py in name_scope(self, name)
   3942         # (viz. '-', '\', '/', and '_').
   3943         if not _VALID_SCOPE_NAME_REGEX.match(name):
-> 3944           raise ValueError("'%s' is not a valid scope name" % name)
   3945       else:
   3946         # Scopes created in the root must match the more restrictive

ValueError: 'Exterior1st_Wd Sdng' is not a valid scope name

我无法理解术语“Exterior1st_Wd Sdng”的含义，因为我没有任何这样命名的变量。提前致谢!

Answer 1

我试图弄清楚 Tensorflow 中允许使用哪些范围名称，而此页面是第一个结果，因此我将借此机会在这里为具有相同查询的其他人发布答案。

在撰写本文时，允许的范围名称似乎受到 this 的限制。 Tensorflow 源代码中的行:

_VALID_SCOPE_NAME_REGEX = re.compile("^[A-Za-z0-9_.\\-/>]*$")

换句话说，作用域名称可以包含字母(大小写)、数字和 _、.、\、-、/、>。 (值得注意的是，它们不能包含空格。)

希望有人觉得这有帮助。