TensorFlow使用next_batch()读取/tensorflow.python.framework.errors_impl.InvalidArgumentError: Expect 3 fi

最新推荐文章于 2025-12-02 21:59:15 发布

原创最新推荐文章于 2025-12-02 21:59:15 发布 · 1.4w 阅读

1 ·

本内容遵循CC 4.0 BY-SA版权协议

收录于

机器学习

Tensorflow

神经网络

分批次读取数据

数据模板：

源代码

-------------------------------------------------

import tensorflow as tf
import numpy as np

def readMyFileFormat(fileNameQueue):
    reader = tf.TextLineReader()
    key, value = reader.read(fileNameQueue)

    record_defaults = [[1.0], [1.0], [1.0]]
    x1, x2, x3 = tf.decode_csv(value, record_defaults=record_defaults)
    features = tf.stack([x1, x2])
    label = x3
    return features, label

def inputPipeLine(fileNames=["Test.csv"], batchSize = 4, numEpochs = None):
    fileNameQueue = tf.train.string_input_producer(fileNames, num_epochs = numEpochs)
    example, label = readMyFileFormat(fileNameQueue)
    min_after_dequeue = 8
    capacity = min_after_dequeue + 3 * batchSize
    exampleBatch, labelBatch = tf.train.shuffle_batch([example, label], batch_size=batchSize, num_threads=3,  capacity=capacity, min_after_dequeue=min_after_dequeue)
    return exampleBatch, labelBatch

featureBatch, labelBatch = inputPipeLine(["Test.csv"], batchSize=4)
with tf.Session() as sess:
    # Start populating the filename queue.
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)
    example, label = sess.run([featureBatch, labelBatch])
    print(example, label)
    coord.request_stop()
    coord.join(threads)
    sess.close()

----------------------------------------------------------------------------------------------------------------------------------------------------

出现错误：

C:/Users/User/PycharmProjects/Test/test.py
2017-09-25 15:04:46.598434: W c:\tf_jenkins\home\workspace\release-win\m\windows\py\35\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE instructions, but these are available on your machine and could speed up CPU computations.
2017-09-25 15:04:46.598711: W c:\tf_jenkins\home\workspace\release-win\m\windows\py\35\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE2 instructions, but these are available on your machine and could speed up CPU computations.
2017-09-25 15:04:46.598974: W c:\tf_jenkins\home\workspace\release-win\m\windows\py\35\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations.
2017-09-25 15:04:46.599224: W c:\tf_jenkins\home\workspace\release-win\m\windows\py\35\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-09-25 15:04:46.599460: W c:\tf_jenkins\home\workspace\release-win\m\windows\py\35\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-09-25 15:04:46.599708: W c:\tf_jenkins\home\workspace\release-win\m\windows\py\35\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-09-25 15:04:46.599948: W c:\tf_jenkins\home\workspace\release-win\m\windows\py\35\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-09-25 15:04:46.600168: W c:\tf_jenkins\home\workspace\release-win\m\windows\py\35\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
[[ 7. 8.]
[ 2. 4.]
[ 1. 2.]
[ 1. 2.]] [ 11. 42. 10. 10.]
Traceback (most recent call last):
File "C:/Users/JZ/PycharmProjects/Test/test.py", line 30, in <module>
coord.join(threads)
File "C:\Users\JZ\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\training\coordinator.py", line 389, in join
six.reraise(*self._exc_info_to_raise)
File "C:\Users\JZ\AppData\Local\Programs\Python\Python35\lib\site-packages\six.py", line 686, in reraise
raise value
File "C:\Users\JZ\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\training\queue_runner_impl.py", line 238, in _run
enqueue_callable()
File "C:\Users\JZ\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1063, in _single_operation_run
target_list_as_strings, status, None)
File "C:\Users\JZ\AppData\Local\Programs\Python\Python35\lib\contextlib.py", line 66, in __exit__
next(self.gen)
File "C:\Users\JZ\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Expect 3 fields but have 0 in record 0
[[Node: DecodeCSV = DecodeCSV[OUT_TYPE=[DT_FLOAT, DT_FLOAT, DT_FLOAT], field_delim=",", _device="/job:localhost/replica:0/task:0/cpu:0"](ReaderReadV2:1, DecodeCSV/record_defaults_0, DecodeCSV/record_defaults_1, DecodeCSV/record_defaults_2)]]

错误原因：很可能是CSV文件数据最后还有多余的行，例如我出现的原因