Empty hypothesis when periods are included in dataset #62
Description
Hello Uri,
I am trying to train the Code2Seq model on the Funcom dataset. I tokenized the dataset by removing all special characters except for periods and commas. When I train a Code2Seq model on this dataset, I get the following error :
Saved after 1 epochs in: models/funcom-test/model_iter1
Finished 1 epochs
Done testing, epoch reached
Traceback (most recent call last):
File "/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1365, in _do_call
return fn(*args)
File "/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1350, in _run_fn
target_list, run_metadata)
File "/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1443, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.OutOfRangeError: 2 root error(s) found.
(0) Out of range: End of sequence
[[{{node IteratorGetNext}}]]
(1) Out of range: End of sequence
[[{{node IteratorGetNext}}]]
[[IteratorGetNext/_27]]
0 successful operations.
0 derived errors ignored.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/vijayantajain/code/experiments/code2seq/model.py", line 96, in train
_, batch_loss = self.sess.run([optimizer, train_loss])
File "/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 956, in run
run_metadata_ptr)
File "/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1180, in _run
feed_dict_tensor, options, run_metadata)
File "/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1359, in _do_run
run_metadata)
File "/opt/conda/lib/python3.7/site-packages/tensorflowI have tried this couple of times by changing model configurations, batch-size but still get this error when the comments have periods.
_core/python/client/session.py", line 1384, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.OutOfRangeError: 2 root error(s) found.
(0) Out of range: End of sequence
[[node IteratorGetNext (defined at /opt/conda/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:1748) ]]
(1) Out of range: End of sequence
[[node IteratorGetNext (defined at /opt/conda/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:1748) ]]
[[IteratorGetNext/_27]]
0 successful operations.
0 derived errors ignored.
Original stack trace for 'IteratorGetNext':
File "code2seq.py", line 39, in <module>
model.train()
File "/home/vijayantajain/code/experiments/code2seq/model.py", line 77, in train
config=self.config)
File "/home/vijayantajain/code/experiments/code2seq/reader.py", line 43, in __init__
self.output_tensors = self.compute_output()
File "/home/vijayantajain/code/experiments/code2seq/reader.py", line 192, in compute_output
return self.iterator.get_next()
File "/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/data/ops/iterator_ops.py", line 426, in get_next
name=name)
File "/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/ops/gen_dataset_ops.py", line 2518, in iterator_get_next
output_shapes=output_shapes, name=name)
File "/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/framework/op_def_library.py", line 794, in _apply_op_helper
op_def=op_def)
File "/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 3357, in create_op
attrs, op_def, compute_device)
File "/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 3426, in _create_op_internal
op_def=op_def)
File "/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 1748, in __init__
self._traceback = tf_stack.extract_stack()
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "code2seq.py", line 39, in <module>
model.train()
File "/home/vijayantajain/code/experiments/code2seq/model.py", line 108, in train
results, precision, recall, f1, rouge = self.evaluate()
File "/home/vijayantajain/code/experiments/code2seq/model.py", line 230, in evaluate
hyp_path=predicted_file_name, ref_path=ref_file_name, avg=True, ignore_empty=True)
File "/opt/conda/lib/python3.7/site-packages/rouge/rouge.py", line 47, in get_scores
ignore_empty=ignore_empty)
File "/opt/conda/lib/python3.7/site-packages/rouge/rouge.py", line 105, in get_scores
return self._get_avg_scores(hyps, refs)
File "/opt/conda/lib/python3.7/site-packages/rouge/rouge.py", line 145, in _get_avg_scores
sc = fn(hyp, ref, exclusive=self.exclusive)
File "/opt/conda/lib/python3.7/site-packages/rouge/rouge.py", line 53, in <lambda>
"rouge-1": lambda hyp, ref, **k: rouge_score.rouge_n(hyp, ref, 1, **k),
File "/opt/conda/lib/python3.7/site-packages/rouge/rouge_score.py", line 253, in rouge_n
raise ValueError("Hypothesis is empty.")
ValueError: Hypothesis is empty.When I check pred.txt in the models directory I see that some lines are empty which is most likely causing the error.
When I remove all special characters in the Funcom dataset, including periods and comma, and train again I do not get this error.
Any idea on why the model would not predict anything for some examples if there are periods and commas in the dataset?
Thanks!
VJ