我正在尝试完成TensorFlow的这个教程: https://www.tensorflow.org/versions/master/tutorials/audio_recognition 在那里,我有兴趣创建一个可以进行语音到文本的简单单词识别。
然而,在成功训练网络之后,下一步(根据教程)将是这样做的:
python tensorflow/examples/speech_commands/freeze.py \
--start_checkpoint=/tmp/speech_commands_train/conv.ckpt-18000 \
--output_file=/tmp/my_frozen_graph.pb
当我这样做时,我收到以下错误:
InvalidArgumentError (see above for traceback): Unsuccessful TensorSliceReader constructor: Failed to get matching files on ./tmp/speech_commands_train/conv.ckpt-18000: Not found: ./tmp/speech_commands_train; No such file or directory
[[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]
要查看整个错误,我创建了这个pastebin:https://pastebin.com/NUBSec6Q
任何人都知道如何解决这个问题?一直在浏览我的目录并摆弄,但似乎无法提出解决方案。