apcode / tensorflow_fasttext Goto Github PK

View Code? Open in Web Editor NEW

302.0 20.0 93.0 60 KB

Simple embedding based text classifier inspired by fastText, implemented in tensorflow

License: MIT License

Python 80.29% Shell 19.71%

fasttext tensorflow language-identification text-classifier

tensorflow_fasttext's People

Contributors

Stargazers

Watchers

Forkers

darrengarvey benjamesbabala stevenlol nb-sommerprosjekt jasonzhengyou naushadzaman cbockman thejusvm akbari59 hkxiron xuhanvsxuhan munichong dotrado kkissmart vpegasus ankit-cliqz chenghuige colemakdvorak lyjsz liwzhi huyangenruc kenhehuang satadru5 junailin nurdun huanwu1990 eminemrain bharatflipkart mhbashari xdaping shelleyhlx luffey1990 hwangjohn dapenggg sqkaer fyweven ziy zouchl gdh756462786 zouxiaoyuonly genlk pkutade nilportugues sysujayce mcdelaney swerwath liujing1036081 tangbogreat shaoguangcheng douhuan tiffen 447555240 datazwer freekite happyyolanda xuanxuangao itsnikka yhjohn163 jiangzhongkai gallupliu matrixplayer xiongeee lsp123 liuwq168 dulimei wangzicui bikong2 zhongyunuestc 13483910551 camel2000 zhengleeee mysqlsc zhaoze92 guoyi0 sycyjl7146 lzpfmh 786440445 ginward timmurnaghan sudeshmu fudp xrosliang coldkey2003 yudian931122 msopengl inistlwq billy-liu-12 stjordanis jackson026 v-smwang yakipudding akamil-etsy

tensorflow_fasttext's Issues

Horovod checkpointing

Should probably get each process to save checkpoint to its own directory.
E.g.
model_dir/hvd.local_rank()/

I think multiple processes are in a race to write checkpoints to the same file.

Support loading facebook pre-trained models

Add option to train word embeddings

ValueError: Shape must be rank 2 but is rank 3 for 'concat' (op: 'ConcatV2') with input shapes: [?,16], [?,1,16], []

Hi,

I'm trying to train text classifier using train_langdetect.shwithout horovod installed.
And I'm getting this error:

  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 1607, in _create_c_op
    c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Shape must be rank 2 but is rank 3 for 'concat' (op: 'ConcatV2') with input shapes: [?,16], [?,1,16], [].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "classifier.py", line 199, in <module>
    tf.app.run()
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_core/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/absl/app.py", line 299, in run
    _run_main(main, args)
  File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/absl/app.py", line 250, in _run_main
    sys.exit(main(argv))
  File "classifier.py", line 193, in main
    FastTrain()
  File "classifier.py", line 167, in FastTrain
    estimator.train(input_fn=train_input, steps=FLAGS.train_steps, hooks=hooks)
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/estimator.py", line 370, in train
    loss = self._train_model(input_fn, hooks, saving_listeners)
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/estimator.py", line 1161, in _train_model
    return self._train_model_default(input_fn, hooks, saving_listeners)
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/estimator.py", line 1191, in _train_model_default
    features, labels, ModeKeys.TRAIN, self.config)
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/estimator.py", line 1149, in _call_model_fn
    model_fn_results = self._model_fn(features=features, **kwargs)
  File "classifier.py", line 118, in model_fn
    input_layer = tf.concat([text_embedding, ngram_embedding], -1)
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_core/python/util/dispatch.py", line 180, in wrapper
    return target(*args, **kwargs)
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_core/python/ops/array_ops.py", line 1420, in concat
    return gen_array_ops.concat_v2(values=values, axis=axis, name=name)
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_core/python/ops/gen_array_ops.py", line 1257, in concat_v2
    "ConcatV2", values=values, axis=axis, name=name)
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_core/python/framework/op_def_library.py", line 794, in _apply_op_helper
    op_def=op_def)
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_core/python/util/deprecation.py", line 507, in new_func
    return func(*args, **kwargs)
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 3357, in create_op
    attrs, op_def, compute_device)
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 3426, in _create_op_internal
    op_def=op_def)
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 1770, in __init__
    control_input_ops)
  File "/Users/kodlan/tensorflow_venv/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 1610, in _create_c_op
    raise ValueError(str(e))
ValueError: Shape must be rank 2 but is rank 3 for 'concat' (op: 'ConcatV2') with input shapes: [?,16], [?,1,16], [].```


Do you have any suggestions what could be causing this?
Thank you.

Create Dockerfile for containerised tensorflow serving service

eval reach a good performance but saved model cannot predict as good as eval

Error during training

Hi,

Thank you for making this code available. I am attempting to run against a simple dataset of mine but I am running into the following error (any pointers):

`Processing training dataset file
Processing test dataset file
data/mydataset.train.vocab
87898
Testing
INFO:tensorflow:Using config: {'_log_step_count_steps': 100, '_master': '', '_evaluation_master': '', '_model_dir': 'data/models/mydataset', '_save_checkpoints_secs': None, '_task_id': 0, '_keep_checkpoint_max': 5, '_task_type': None, '_tf_random_seed': None, '_num_worker_replicas': 0, '_save_checkpoints_steps': 1000, '_session_config': , '_save_summary_steps': 100, '_is_chief': True, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x117c32e80>, '_num_ps_replicas': 0, '_tf_config': gpu_options {
per_process_gpu_memory_fraction: 1
}
, '_environment': 'local', '_keep_checkpoint_every_n_hours': 10000}
STARTING TRAIN
ParseSpec {'label': FixedLenFeature(shape=(1,), dtype=tf.int64, default_value=None), 'text': VarLenFeature(dtype=tf.string)}
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Saving checkpoints for 1 into data/models/mydataset/model.ckpt.
INFO:tensorflow:loss = 3.87008, step = 1
2017-08-23 14:27:17.797448: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Received a label value of -1 which is outside the valid range of [0, 47). Label values: 19 41 22 19 31 1 39 8 22 4 43 12 27 39 19 43 22 44 21 19 4 42 19 21 27 9 41 6 41 44 1 14 5 6 37 6 41 1 6 16 42 39 4 0 25 14 4 30 6 31 9 19 41 41 41 6 23 1 19 19 9 17 26 41 43 19 41 23 22 14 14 9 6 41 1 1 -1 6 23 31 16 14 20 6 41 19 4 1 21 31 23 34 4 6 11 6 1 4 30 32 44 17 43 4 44 32 13 9 44 4 41 41 4 6 9 19 22 40 9 23 4 21 41 0 6 5 20 37
Traceback (most recent call last):
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1327, in _do_call
return fn(*args)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1306, in _run_fn
status, run_metadata)
File "/anaconda3/lib/python3.5/contextlib.py", line 66, in exit
next(self.gen)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Received a label value of -1 which is outside the valid range of [0, 47). Label values: 19 41 22 19 31 1 39 8 22 4 43 12 27 39 19 43 22 44 21 19 4 42 19 21 27 9 41 6 41 44 1 14 5 6 37 6 41 1 6 16 42 39 4 0 25 14 4 30 6 31 9 19 41 41 41 6 23 1 19 19 9 17 26 41 43 19 41 23 22 14 14 9 6 41 1 1 -1 6 23 31 16 14 20 6 41 19 4 1 21 31 23 34 4 6 11 6 1 4 30 32 44 17 43 4 44 32 13 9 44 4 41 41 4 6 9 19 22 40 9 23 4 21 41 0 6 5 20 37
[[Node: SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits = SparseSoftmaxCrossEntropyWithLogits[T=DT_FLOAT, Tlabels=DT_INT64, _device="/job:localhost/replica:0/task:0/cpu:0"](SparseSoftmaxCrossEntropyWithLogits/Reshape, SparseSoftmaxCrossEntropyWithLogits/Reshape_1)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "classifier.py", line 218, in
tf.app.run()
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "classifier.py", line 208, in main
FastTrain()
File "classifier.py", line 181, in FastTrain
estimator.train(input_fn=train_input, steps=FLAGS.train_steps, hooks=None)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py", line 241, in train
loss = self._train_model(input_fn=input_fn, hooks=hooks)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py", line 686, in _train_model
_, loss = mon_sess.run([estimator_spec.train_op, estimator_spec.loss])
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/training/monitored_session.py", line 518, in run
run_metadata=run_metadata)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/training/monitored_session.py", line 862, in run
run_metadata=run_metadata)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/training/monitored_session.py", line 818, in run
return self._sess.run(*args, **kwargs)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/training/monitored_session.py", line 972, in run
run_metadata=run_metadata)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/training/monitored_session.py", line 818, in run
return self._sess.run(*args, **kwargs)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1124, in _run
feed_dict_tensor, options, run_metadata)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1321, in _do_run
options, run_metadata)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1340, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Received a label value of -1 which is outside the valid range of [0, 47). Label values: 19 41 22 19 31 1 39 8 22 4 43 12 27 39 19 43 22 44 21 19 4 42 19 21 27 9 41 6 41 44 1 14 5 6 37 6 41 1 6 16 42 39 4 0 25 14 4 30 6 31 9 19 41 41 41 6 23 1 19 19 9 17 26 41 43 19 41 23 22 14 14 9 6 41 1 1 -1 6 23 31 16 14 20 6 41 19 4 1 21 31 23 34 4 6 11 6 1 4 30 32 44 17 43 4 44 32 13 9 44 4 41 41 4 6 9 19 22 40 9 23 4 21 41 0 6 5 20 37
[[Node: SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits = SparseSoftmaxCrossEntropyWithLogits[T=DT_FLOAT, Tlabels=DT_INT64, _device="/job:localhost/replica:0/task:0/cpu:0"](SparseSoftmaxCrossEntropyWithLogits/Reshape, SparseSoftmaxCrossEntropyWithLogits/Reshape_1)]]

Caused by op 'SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits', defined at:
File "classifier.py", line 218, in
tf.app.run()
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "classifier.py", line 208, in main
FastTrain()
File "classifier.py", line 181, in FastTrain
estimator.train(input_fn=train_input, steps=FLAGS.train_steps, hooks=None)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py", line 241, in train
loss = self._train_model(input_fn=input_fn, hooks=hooks)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py", line 630, in _train_model
model_fn_lib.ModeKeys.TRAIN)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py", line 615, in _call_model_fn
model_fn_results = self._model_fn(features=features, **kwargs)
File "classifier.py", line 121, in model_fn
labels=labels, logits=logits))
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/ops/nn_ops.py", line 1706, in sparse_softmax_cross_entropy_with_logits
precise_logits, labels, name=name)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 2491, in _sparse_softmax_cross_entropy_with_logits
features=features, labels=labels, name=name)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
op_def=op_def)
File "/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2630, in create_op
original_op=self._default_original_op, op_def=op_def)
File "~/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1204, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): Received a label value of -1 which is outside the valid range of [0, 47). Label values: 19 41 22 19 31 1 39 8 22 4 43 12 27 39 19 43 22 44 21 19 4 42 19 21 27 9 41 6 41 44 1 14 5 6 37 6 41 1 6 16 42 39 4 0 25 14 4 30 6 31 9 19 41 41 41 6 23 1 19 19 9 17 26 41 43 19 41 23 22 14 14 9 6 41 1 1 -1 6 23 31 16 14 20 6 41 19 4 1 21 31 23 34 4 6 11 6 1 4 30 32 44 17 43 4 44 32 13 9 44 4 41 41 4 6 9 19 22 40 9 23 4 21 41 0 6 5 20 37
[[Node: SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits = SparseSoftmaxCrossEntropyWithLogits[T=DT_FLOAT, Tlabels=DT_INT64, _device="/job:localhost/replica:0/task:0/cpu:0"](SparseSoftmaxCrossEntropyWithLogits/Reshape, SparseSoftmaxCrossEntropyWithLogits/Reshape_1)]]
`

The same mydataset.train / mydataset.test is processed fine by fasttext (C++ version). Thank yoiiu in advance!

eval reach a good performance but saved model cannot predict as good as eval

`DataLossError: corrupted record` during training

Hello, during training the following error occurs:

tensorflow.python.framework.errors_impl.DataLossError: corrupted record at 0
[[{{node read_batch_features/read/ReaderReadUpToV2}} = ReaderReadUpToV2[_device="/job:localhost/replica:0/task:0/device:CPU:0"](read_batch_features/read/TFRecordReaderV2, read_batch_features/file_name_queue, read_batch_features/read/ReaderReadUpToV2/num_records)]]

My environment is:
Python 3.6,
tensorflow 1.12.0,
macOS 10.13

Here is detailed information:

python3 classifier.py
--train_records=data/train-label-text.txt
--eval_records=data/train-label-text.txt
--label_file=data/train-label-text.txt.labels
--vocab_file=data/train-label-text.txt.vocab
--model_dir=model
--export_dir=model
FastTrain 1000
WARNING:tensorflow:From classifier.py:153: RunConfig.init (from tensorflow.contrib.learn.python.learn.estimators.run_config) is deprecated and will be removed in a future version.
Instructions for updating:
When switching to tf.estimator.Estimator, use tf.estimator.RunConfig instead.
TESTdata/train-label-text.txt
STARTING TRAIN
ParseSpec {'text': VarLenFeature(dtype=tf.string), 'label': FixedLenFeature(shape=(), dtype=tf.string, default_value=None)}
Input file: data/train-label-text.txt
WARNING:tensorflow:From /Users/hans/repos/simple-tests/classify/workspace/inputs.py:54: read_batch_features (from tensorflow.contrib.learn.python.learn.learn_io.graph_io) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.data.
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/learn_io/graph_io.py:833: read_keyed_batch_features (from tensorflow.contrib.learn.python.learn.learn_io.graph_io) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.data.
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/learn_io/graph_io.py:542: read_keyed_batch_examples (from tensorflow.contrib.learn.python.learn.learn_io.graph_io) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.data.
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/learn_io/graph_io.py:423: string_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensor_slices(string_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs). If shuffle=False, omit the .shuffle(...).
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/training/input.py:276: input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensor_slices(input_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs). If shuffle=False, omit the .shuffle(...).
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/training/input.py:188: limit_epochs (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensors(tensor).repeat(num_epochs).
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/training/input.py:197: QueueRunner.init (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the tf.data module.
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/training/input.py:197: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the tf.data module.
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/learn_io/graph_io.py:317: TFRecordReader.init (from tensorflow.python.ops.io_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.TFRecordDataset.
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/learn_io/graph_io.py:449: shuffle_batch_join (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.interleave(...).shuffle(min_after_dequeue).batch(batch_size).
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/learn_io/graph_io.py:550: queue_parsed_features (from tensorflow.contrib.learn.python.learn.learn_io.graph_io) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.data.
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/ops/sparse_ops.py:1165: sparse_to_dense (from tensorflow.python.ops.sparse_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Create a tf.sparse.SparseTensor and use tf.sparse.to_dense instead.
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py:804: start_queue_runners (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the tf.data module.
Traceback (most recent call last):
File "classifier.py", line 199, in
tf.app.run()
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "classifier.py", line 193, in main
FastTrain()
File "classifier.py", line 167, in FastTrain
estimator.train(input_fn=train_input, steps=FLAGS.train_steps, hooks=hooks)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 354, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1207, in _train_model
return self._train_model_default(input_fn, hooks, saving_listeners)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1241, in _train_model_default
saving_listeners)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1471, in _train_with_estimator_spec
_, loss = mon_sess.run([estimator_spec.train_op, estimator_spec.loss])
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 783, in exit
self._close_internal(exception_type)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 821, in _close_internal
self._sess.close()
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 1069, in close
self._sess.close()
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 1229, in close
ignore_live_threads=True)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/training/coordinator.py", line 389, in join
six.reraise(*self._exc_info_to_raise)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/six.py", line 692, in reraise
raise value.with_traceback(tb)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/training/queue_runner_impl.py", line 257, in _run
enqueue_callable()
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1257, in _single_operation_run
self._call_tf_sessionrun(None, {}, [], target_list, None)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1407, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.DataLossError: corrupted record at 0
[[{{node read_batch_features/read/ReaderReadUpToV2}} = ReaderReadUpToV2[_device="/job:localhost/replica:0/task:0/device:CPU:0"](read_batch_features/read/TFRecordReaderV2, read_batch_features/file_name_queue, read_batch_features/read/ReaderReadUpToV2/num_records)]]

ngrams maybe contains bug

def GenerateNgrams(words, ngrams):
    nglist = []
    for ng in ngrams:
        for word in words:
            nglist.extend([word[n:n+ng] for n in range(len(word)-ng+1)])
    return ngli

maybe it should like following

def GenerateNgrams(words, ngrams):
    nglist = []
    for ng in ngrams:
        nglist.extend(''.join([words[n:n+ng]) for n in range(len(words)-ng+1)])
    return ngli

apcode / tensorflow_fasttext Goto Github PK

tensorflow_fasttext's People

Contributors

Stargazers

Watchers

Forkers

tensorflow_fasttext's Issues

Horovod checkpointing

Support loading facebook pre-trained models

Add option to train word embeddings

ValueError: Shape must be rank 2 but is rank 3 for 'concat' (op: 'ConcatV2') with input shapes: [?,16], [?,1,16], []

Create Dockerfile for containerised tensorflow serving service

eval reach a good performance but saved model cannot predict as good as eval

Error during training

eval reach a good performance but saved model cannot predict as good as eval

`DataLossError: corrupted record` during training

ngrams maybe contains bug

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent