Question

更新后的帖子：

我调查了最初的建议，以找到问题的根源。最初的问题是几个要素列产生了属性错误（“无名”或“ get_sparse_tensors”）

这是“ tuple”对象没有属性“ name”的示例代码：

metro = tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_identity("metro",94)),
tf.feature_column.indicator_column(metro),

“地铁”列中的数据如下所示：

 -"(not set)"
 -"Abilene-Sweetwater TX"
 -"Albany-Schenectady-Troy NY"               
 -"Atlanta GA"
  -...

这是_get_sparse_tensor错误的示例代码：

browser = tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_identity("browser",54))
tf.feature_column.indicator_column(browser),

我可以通过将categorical_column_with_identity替换为categorical_column_with_vocabulary_list来解决这两个错误

 metro = tf.feature_column.categorical_column_with_vocabulary_list('metro',
                                                                      vocabulary_list=['(not set)','Abilene-Sweetwater TX','Albany-Schenectady-Troy NY','Atlanta GA'])

由于使用tf.feature_column.categorical_column_with_identity比编写长词汇表要快得多，所以我很想知道为什么会出现此错误？

这是MCVE：

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

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


# specify col.names.
names = [
    'browser',
    'metro',
    'transactionRevenue'
 ]

# specify dtypes.
dtypes = {
     'browser': str,
     'metro': str,
     'transactionRevenue': np.float32
}


 df = pd.read_csv('dropped_train.csv', names=names, dtype=dtypes, n   a_values='?',encoding ="ISO-8859-1")

 def load_data(y_name="transactionRevenue", train_fraction=0.7, seed=None):
    # Load the raw data columns.
     data = df
    # Shuffle the data
     np.random.seed(seed)

    # Split the data into train/test subsets.
     x_train = data.sample(frac=train_fraction, random_state=seed)
     x_test = data.drop(x_train.index)

    # Extract the label from the features DataFrame.
     y_train = x_train.pop(y_name)
     y_test = x_test.pop(y_name)

    return (x_train, y_train), (x_test, y_test)

 load_data()

 def features_columns():
    metro = tf.feature_column.indicator_column  (tf.feature_column.categorical_column_with_identity("metro",94)),
    browser = tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_identity("browser",54))


    feature_columns = [
        tf.feature_column.indicator_column(browser),
        tf.feature_column.indicator_column(metro)
        ]
    return feature_columns

 features_columns()

log_dir = ("C:\\…\\gs sales\\model")
parser = argparse.ArgumentParser()
parser.add_argument('--batch_size', default=500, type=int, help='batch size')
parser.add_argument('--train_steps', default=10000, type=int, help='number of training steps')
parser.add_argument('--norm_factor', default=10., type=float, help='normalization factor')


 def main(argv):
    """Builds, trains, and evaluates the model."""
    args = parser.parse_args(argv[1:])

    (train_x, train_y), (test_x, test_y) = load_data()

    train_y /= args.norm_factor
    test_y /= args.norm_factor

    # Build the training dataset.
    training_input_fn = tf.estimator.inputs.pandas_input_fn(x=train_x,   y=train_y, batch_size=64,
                                                        shuffle=True, num_epochs=None)

    # Build the Estimator.

    model = tf.estimator.DNNRegressor(hidden_units=[50,30,10],  feature_columns=features_columns(),
                                  model_dir=log_dir)

     # Train the model.
    model.train(input_fn=training_input_fn, steps=args.train_steps)



if __name__ == "__main__":
    tf.logging.set_verbosity(tf.logging.INFO)
    tf.app.run(main=main)

tf.feature_column.categorical_column_with_identity错误：对象没有属性“名称”或“ get_sparse_tensors”

0 个答案: