Tensorflow：常见错误

Love The Way You Lie 2022-06-12 09:20 327阅读 0赞

## Tensorflow SSE报错 ##

TensorFlow wasn't compiled to use SSE (etc.) instructions, but these are available

解决：os.environ\['TF\_CPP\_MIN\_LOG\_LEVEL'\]='2'

\[[TensorFlow wasn't compiled to use SSE (etc.) instructions, but these are available][TensorFlow wasn_t compiled to use SSE _etc._ instructions_ but these are available]\]

参数出错

beta = tf.Variable(beta0, name='beta') #不能这么写，l2计算就马上出错，变为nan

改为

beta = tf.Constant(beta0)

### 0.12 Saver.restore broken? Unsuccessful TensorSliceReader constructor: Failed to find any matching files ###

saver.restore训练好的模型出错saver.restore(*sess*, checkpoint\_path)

解决：

1.  use a model name without the character `[]，即要回复的模型文件名中不能含有[]`
2.  when you tried to restore, use the full relative path `./model_epoch10` rather than `model_epoch10`
3.      FLAGS = tf.flags.FLAGS
        tf.flags.DEFINE_string("checkpoint_path","","...")
    
    后面如果再定义FLAGS.checkpoint\_path = "./.../..."是无效的，也就是说FLAGS.\*\*\*是不能赋值的！导致出错。

\[[0.12 Saver.restore broken?][0.12 Saver.restore broken]\]

### tensorflow.python.framework.errors\_impl.NotFoundError: FindFirstFile failed for:... ###

checkpoint\_path = tf.train.latest\_checkpoint(*checkpoint\_path*)

训练结果的文件夹居然要和恢复时文件所在文件夹一样（训练文件夹不能改名字）！不然就会报错。

### RuntimeError: Coordinator stopped with threads still running: Thread-4 ###

tf.contrib.slim.learning.train(..., saver=saver)  \# 模型中间结果保存时出错

sv.saver.save(sess, sv.save\_path, global\_step=sv.global\_step)

解决：1 use tf.reset\_default\_graph() to reset the graph instead of using with tf.Graph().as\_default()

\[["Coordinator stopped with threads still running" happens when using cross-validation][Coordinator stopped with threads still running_ happens when using cross-validation]\]

\[[coord.request\_stop() doesn't stop the threads][coord.request_stop_ doesn_t stop the threads]\]

### ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape\[2580,200\] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU\_0\_bfc ###

error显示的是gpu0的内存耗尽了，可能是多用户时其它用户使用中，这时可以通过nvidia-smi查看gpu使用情况，并在代码中指定使用其它闲置的gpu如gpu1：os.environ\["CUDA\_VISIBLE\_DEVICES"\] = "1"。

from: [\-柚子皮-][-_-]

ref:

[TensorFlow wasn_t compiled to use SSE _etc._ instructions_ but these are available]: https://stackoverflow.com/questions/43134753/tensorflow-wasnt-compiled-to-use-sse-etc-instructions-but-these-are-availab
[0.12 Saver.restore broken]: https://github.com/tensorflow/tensorflow/issues/6082
[Coordinator stopped with threads still running_ happens when using cross-validation]: https://github.com/tflearn/tflearn/issues/313
[coord.request_stop_ doesn_t stop the threads]: https://github.com/tensorflow/tensorflow/issues/2130
[-_-]: https://me.csdn.net/pipisorry