I am trying to run allennlp package's prediction using a model which I have trained over my training data. However, at the beginning of the process, this exception comes up and halts the program.
raise source.error('bad escape %s' % escape, len(escape)) sre_constants.error: bad escape \p at position 257
Also, when I open an allennlp environment, I'm getting another error:
2019-04-01 12:20:43,879 - INFO - allennlp.common.params - dataset_reader.lazy = False Segmentation fault (core dumped)
I'm doing a sequence-to-sequence task where the training data is a bunch of 0 and 1's (src and target) using the following command:
CUDA_VISBILE_DEVICES=1 python -m allennlp.run train
allennlp_config/simple_tagger.json
--serialization-dir models/last
And in prediction:
python -m allennlp.run predict models/new1/model.tar.gz
data/test.src.txt
--output bu-out.txt
--cuda-device 0
--batch-size 5
To be specific, I try re-producing the results in this repo: https://github.com/sebastianGehrmann/bottom-up-summary
