Question

以下代码：

import numpy as np
import tensorflow as tf
from sklearn.model_selection import train_test_split
import pandas as pd



# DATA PREPARE
df = pd.read_csv('housing.csv')
df = df.dropna()
print(df.head)
print(df.describe())
print(df.info())



# NORMALIZATION
from sklearn.preprocessing import MinMaxScaler

scaler = MinMaxScaler()
scaler.fit(df[['housing_median_age', 'total_rooms', 'total_bedrooms', 'population', 'households', 'median_income',
               'median_house_value']])
df_scaled_cols = scaler.transform(df[['housing_median_age', 'total_rooms', 'total_bedrooms',
                                      'population', 'households', 'median_income', 'median_house_value']])
df_scaled_cols = pd.DataFrame(data=df_scaled_cols, columns=['housing_median_age', 'total_rooms', 'total_bedrooms',
                                                            'population', 'households', 'median_income',
                                                            'median_house_value'])

df = pd.concat([df_scaled_cols, df['ocean_proximity']], axis=1)



# DATAFRAME INTO X AND Y -> TRAIN TEST SPLIT
x_data = df[['housing_median_age', 'total_rooms', 'total_bedrooms', 'population', 'households', 'median_income',
             'ocean_proximity']]
y_label = df['median_house_value']

X_train, X_test, y_train, y_test = train_test_split(x_data, y_label, test_size=0.3)



# FEATURE COLUMNS FROM DATA

m_age = tf.feature_column.numeric_column('housing_median_age')
rooms = tf.feature_column.numeric_column('total_rooms')
bedrooms = tf.feature_column.numeric_column('total_bedrooms')
population = tf.feature_column.numeric_column('population')
households = tf.feature_column.numeric_column('households')
income = tf.feature_column.numeric_column('median_income')
ocean = tf.feature_column.categorical_column_with_hash_bucket('ocean_proximity', hash_bucket_size=10)
embedded_ocean = tf.feature_column.embedding_column(ocean, dimension=4)

feat_cols = [m_age, rooms, bedrooms, population, households, income, embedded_ocean]



# 3 INPUT FUNCTIONS

train_input_func = tf.estimator.inputs.pandas_input_fn(x=X_train, y=y_train, batch_size=10, num_epochs=1000,
                                                       shuffle=True)
test_input_func = tf.estimator.inputs.pandas_input_fn(x=X_test, y=y_test, batch_size=10, num_epochs=1, shuffle=False)
predict_input_func = tf.estimator.inputs.pandas_input_fn(x=X_test, batch_size=10, num_epochs=1, shuffle=False)



# DNN_Reg MODEL

dnn_model = tf.estimator.DNNRegressor(hidden_units=[10,10,10], feature_columns=feat_cols)
dnn_model.train(input_fn=train_input_func, steps=1000)

导致错误：

回溯（最近通话最近）：文件   “ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ client \ session.py”，   1278行，_do_call       返回fn（* args）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ client \ session.py”，   _run_fn中的第1263行       选项，feed_dict，fetch_list，target_list，run_metadata）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ client \ session.py”，   第1350行，在_call_tf_sessionrun中       run_metadata）tensorflow.python.framework.errors_impl.InternalError：无法获取   元素以字节为单位。

在处理上述异常期间，发生了另一个异常：

回溯（最近通话最近）：文件   “ C：/用户/管理员/文档/PycharmProjects/TF_Regression_Project/project.py”，   第69行，在       dnn_model.train（input_fn = train_input_func，步骤= 1000）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ estimator \ estimator.py”，   376号线，在火车上       损失= self._train_model（input_fn，hook，saving_listeners）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ estimator \ estimator.py”，   第1145行，在_train_model中       返回self._train_model_default（input_fn，hooks，saving_listeners）文件   “ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ estimator \ estimator.py”，   第1173行，在_train_model_default中       Saving_listeners）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ estimator \ estimator.py”，   第1451行，在_train_with_estimator_spec中       _，损失= mon_sess.run（[estimator_spec.train_op，estimator_spec.loss]）文件   “ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ training \ monitored_session.py”，   第695行，退出       self._close_internal（exception_type）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ training \ monitored_session.py”，   _close_internal中的第732行       self._sess.close（）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ training \ monitored_session.py”，   980号线，关闭       self._sess.close（）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ training \ monitored_session.py”，   1124行，处于关闭状态       ignore_live_threads = True）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ training \ coordinator.py”，   389行，加入       six.reraise（* self._exc_info_to_raise）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ six.py”，   复线692       提高价值。with_traceback（tb）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ estimator \ inputs \ queues \ feeding_queue_runner.py”，   _run中的第94行       sess.run（enqueue_op，feed_dict = feed_dict）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ client \ session.py”，   877行，正在运行       run_metadata_ptr）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ client \ session.py”，   _run中的第1100行       feed_dict_tensor，选项，run_metadata）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ client \ session.py”，   _do_run中的第1272行       run_metadata）文件“ C：\ Users \ Admin \ AppData \ Local \ Programs \ Python \ Python36 \ lib \ site-packages \ tensorflow \ python \ client \ session.py”，   _do_call中的第1291行       提高类型（e）（node_def，op，message）tensorflow.python.framework.errors_impl.InternalError：无法获取   元素以字节为单位。

里面有什么问题？

Answer 1

问题是归一化。

我执行了以下操作，而不是sklearn方法：

df[['housing_median_age', 'total_rooms', 'total_bedrooms', 'population', 'households', 'median_income',
    'median_house_value']] = df[['housing_median_age', 'total_rooms', 'total_bedrooms', 'population', 'households', 'median_income',
               'median_house_value']].apply(lambda x: (x-x.min()) / (x.max()-x.min()))

因此，总而言之，我做的事情与sklearn相同，但手动操作-使用lambda。

Tensorflow-“无法将元素作为字节获取”错误

1 个答案: