CODEWITHSUNDEEP
tensorflowbazel
Dep
Dep

Reputation: 11

TensorFlow Error

I'm trying to run this example (https://github.com/tensorflow/models/tree/master/textsum). when I run this statement:

bazel-bin/textsum/seq2seq_attention \
  --mode=train \
  --article_key=article \
  --abstract_key=abstract \
  --data_path=data/training-* \
  --vocab_path=data/vocab \
  --log_root=textsum/log_root \
  --train_dir=textsum/log_root/train

I see the following output

  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 30, in run
    sys.exit(main(sys.argv[:1] + flags_passthrough))

  File "/home/depiano/Scrivania/TextSummarization/bazel-bin/textsum/seq2seq_attention.runfiles/__main__/textsum/seq2seq_attention.py", line 196, in main
    _Train(model, batcher)

  File "/home/depiano/Scrivania/TextSummarization/bazel-bin/textsum/seq2seq_attention.runfiles/__main__/textsum/seq2seq_attention.py", line 98, in _Train
    allow_soft_placement=True))

  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/supervisor.py", line 715, in prepare_or_wait_for_session
    init_feed_dict=self._init_feed_dict, init_fn=self._init_fn)

  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/session_manager.py", line 227, in prepare_session
    config=config)

  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/session_manager.py", line 173, in _restore_checkpoint
    saver.restore(sess, ckpt.model_checkpoint_path)

  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1342, in restore
    "File path is: %r" % (save_path, file_path))

ValueError: Restore called with invalid save path: u'textsum/log_root/model.ckpt-0'. File path is: u'textsum/log_root/model.ckpt-0'
Errore di segmentazione (core dump creato)

Upvotes: 0

Views: 196

Answers (2)

Shamane Siriwardhana
Shamane Siriwardhana

Reputation: 4201

Here what happens is tensorflow trying to load previously saved parameters in to the graph module.They can be architectural details and other initialization things. This is how tf test if there's a pretrained module 

ckpt =tf.train.get_checkpoint_state(os.path.dirname('c/checkpointsq'))
    # if that checkpoint exists, restore from checkpoint
    if ckpt and ckpt.model_checkpoint_path:
        print("Restoring the checkpoins")
        saver.restore(sess, ckpt.model_checkpoint_path)

Here the first function will return a ckpt file object if there's any file called checkpoint. It's text file. Inside it there will be details of your network. So you have to correct the log directory in your case.

Upvotes: 0

Raingo Lee
Raingo Lee

Reputation: 45

The error indicates your model file textsum/log_root/model.ckpt-0 does not exist or can not be created. Make sure the directory textsum/log_root exist.

Upvotes: 1

Related Questions