Skip to content
Snippets Groups Projects
Unverified Commit 40cf553e authored by Daniel Ecer's avatar Daniel Ecer Committed by GitHub
Browse files

allow partial data generation (#55)

parent 7c7a1196
No related branches found
No related tags found
No related merge requests found
......@@ -24,5 +24,15 @@ RAW_TRAINING_DATA_DIR=/tmp/raw-training-data
rm -rf "${RAW_TRAINING_DATA_DIR}"
generate-raw-grobid-training-data.sh "${PDF_DIR}" "${RAW_TRAINING_DATA_DIR}"
if generate-raw-grobid-training-data.sh "${PDF_DIR}" "${RAW_TRAINING_DATA_DIR}"; then
echo "generated raw grobid training data: ${RAW_TRAINING_DATA_DIR}"
else
echo "failed to generate raw grobid training data, error: $?"
fi
if [ ! "$(ls --almost-all ${RAW_TRAINING_DATA_DIR})" ]; then
echo "no raw grobid training data generated: ${RAW_TRAINING_DATA_DIR}"
exit 1
fi
copy-raw-training-data-to-file-structure.sh "${RAW_TRAINING_DATA_DIR}" "${DATASET_DIR}"
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment