首页 文章

适用于LinearRegressor的代码返回AttributeError：'Tensor' object对于DynamicRnnEstimator没有属性'get'

提问于
浏览 次
2

一开始，我需要说我使用的是TF v 1.1 .

代码：

import random
import tensorflow as tf

xData = []
yData = []
for _ in range(10000):
    x = random.random()
    xData.append(x)
    y = 2 * x
    yData.append(y)


xc = tf.contrib.layers.real_valued_column("")
estimator = tf.contrib.learn.DynamicRnnEstimator(problem_type = constants.ProblemType.LINEAR_REGRESSION,
                                                 prediction_type = PredictionType.SINGLE_VALUE,
                                                 sequence_feature_columns = [xc],
                                                 context_feature_columns = None,
                                                 num_units = 5,
                                                 cell_type = 'lstm', 
                                                 optimizer = 'SGD',
                                                 learning_rate = '0.1')

def get_train_inputs():
  x = tf.constant(xData)
  y = tf.constant(yData)

  return x, y

estimator.fit(input_fn=get_train_inputs, steps=TRAINING_STEPS)

我有：

AttributeError：'Tensor'对象没有属性'get'

这里 . 相同的代码适用于LinearRegressor而不是DynamicRnnEstimator .

警告：tensorflow：来自E：\ Python35 \ lib \ site-packages \ tensorflow \ contrib \ learn \ python \ learn \ estimators \ dynamic_rnn_estimator.py:724：regression_target（来自tensorflow.contrib.layers.python.layers.target_column）已弃用，将于2016-11-12之后删除 . 更新说明：此文件将在弃用日期后删除 . 请切换到third_party / tensorflow / contrib / learn / python / learn / estimators / head.py警告：tensorflow：使用临时文件夹作为模型目录：C：\ Users \ pavel \ AppData \ Local \ Temp \ tmpzy68t_iw Blockquote Traceback（最近一次调用最后一次）：文件“C：/Users/pavel/PycharmProjects/rnnEstimator/main.py”，第31行，在estimator.fit中（input_fn = get_train_inputs，steps = 1000）文件“E：\ Python35 \ lib \ site-packages \ tensorflow \ python \ util \ deprecation.py”，第281行，在new_func中返回func（* args，** kwargs）文件“E：\ Python35 \ lib \ site-packages \ tensorflow \ contrib \ learn \ python \ learn \ estimators \ estimator.py“，第430行，在fit loss = self._train_model（input_fn = input_fn，hooks = hooks）文件”E：\ Python35 \ lib \ site -packages \ tensorflow \ contrib \ learn \ python \ learn \ estimators \ estimator.py“，第927行，在_train_model中model_fn_ops = self._get_train_ops（features，labels）文件”E：\ Python35 \ lib \ site-packages \ tensorflow \的contrib \学习\ python的\学习\ê stimators \ estimator.py“，第1132行，在_get_train_ops中返回self._call_model_fn（features，labels，model_fn_lib.ModeKeys.TRAIN）文件”E：\ Python35 \ lib \ site-packages \ tensorflow \ contrib \ learn \ python \ learn \ estimators \ estimator.py“，第1103行，在_call_model_fn中model_fn_results = self._model_fn（features，labels，** kwargs）文件”E：\ Python35 \ lib \ site-packages \ tensorflow \ contrib \ learn \ python \ learn \ estimators \ dynamic_rnn_estimator.py“，第516行，_dynamic_rnn_model_fn sequence_length = features.get（sequence_length_key）AttributeError：'Tensor'对象没有属性'get'

更新：Issue in TF repo's

tensorflow

1 回答

  • 2
    BATCH_SIZE = 32
SEQUENCE_LENGTH = 16


xc = tf.contrib.layers.real_valued_column("")
estimator = tf.contrib.learn.DynamicRnnEstimator(problem_type = constants.ProblemType.LINEAR_REGRESSION,
                                                 prediction_type = PredictionType.SINGLE_VALUE,
                                                 sequence_feature_columns = [xc],
                                                 context_feature_columns = None,
                                                 num_units = 5,
                                                 cell_type = 'lstm', 
                                                 optimizer = 'SGD',
                                                 learning_rate = 0.1)

def get_train_inputs():
  x = tf.random_uniform([BATCH_SIZE, SEQUENCE_LENGTH])
  y = tf.reduce_mean(x, axis=1)
  x = tf.expand_dims(x, axis=2)
  return {"": x}, y

estimator.fit(input_fn=get_train_inputs, steps=1000)
    回复于

相关问题