Question

我正在尝试使用我自己的课程重新训练冰点模型。

我在做什么

我的目录包含

等图像

水玻璃
水瓶
人
椅
.......

我运行以下命令

`python ~/tensorflow/tensorflow/examples/image_retraining/retrain.py \
--bottleneck_dir=/tmp/bottlenecks_new \
--output_graph= output/retrained_graph.pb \
--output_labels= output/retrained_labels.txt \
--image_dir  ~/newimage_dir \
--how_many_training_steps 10000 \
--random_crop=8  \
--random_scale=8 \
--random_brightness=8 \
--train_batch_size=64`

结果

我接受过网络培训，测试准确率为94.6％，但有错误。

回溯

`Final test accuracy = 94.6% (N=613)
Converted 2 variables to const ops.
Traceback (most recent call last):
  File "/home/hannan/tensorflow/tensorflow/examples/image_retraining/retrain.py", line 1061, in <module> tf.app.run(main=main, argv=[sys.argv[0]] + unparsed) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 44, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "/home/hannan/tensorflow/tensorflow/examples/image_retraining/retrain.py", line 902, in main
    f.write(output_graph_def.SerializeToString())
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/lib/io/file_io.py", line 98, in write self._prewrite_check()
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/lib/io/file_io.py", line 84, in _prewrite_check
    compat.as_bytes(self.__name), compat.as_bytes(self.__mode), status)
  File "/usr/lib/python2.7/contextlib.py", line 24, in __exit__
    self.gen.next()
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/errors_impl.py", line 469, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.FailedPreconditionError
`

我尝试了什么

我已卸载tensorflow并从源代码重新安装，工作正常。我已经搜索了错误，只有我理解的是我遇到的错误是由于一些un初始化变量。但是从stacktrace我无法解决错误。

初始再培训错误：tensorflow.python.framework.errors_impl.FailedPreconditionError

0 个答案: