首页 > 解决方案 > NotFoundError:无法从 /content/training/ckpt-9 的检查点或 SavedModel 恢复:

问题描述

我正在尝试在 Google Colaboratory 上实现这个项目,但我已经被同一个错误困住了一段时间。

一切都很好,直到项目的“27”部分。这是我遇到的错误:


/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/py_checkpoint_reader.py in NewCheckpointReader(filepattern)
     95   try:
---> 96     return CheckpointReader(compat.as_bytes(filepattern))
     97   # TODO(b/143319754): Remove the RuntimeError casting logic once we resolve the

RuntimeError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /content/training/ckpt-9

During handling of the above exception, another exception occurred:

NotFoundError                             Traceback (most recent call last)
6 frames
NotFoundError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /content/training/ckpt-9

During handling of the above exception, another exception occurred:

NotFoundError                             Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/util.py in restore(self, save_path, options)
   2338           None, None,
   2339           "Failed to restore from checkpoint or SavedModel at {}: {}".format(
-> 2340               orig_save_path, e.message))
   2341     # Create the save counter now so it gets initialized with other variables
   2342     # when graph building. Creating it earlier would lead to errors when using,

NotFoundError: Failed to restore from checkpoint or SavedModel at /content/training/ckpt-9: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /content/training/ckpt-9```

标签: pythontensorflowgoogle-colaboratory

解决方案


推荐阅读