From 11ce8d3de5894f5055de41921483f3ed8af65a0e Mon Sep 17 00:00:00 2001 From: Gustaf Rydholm Date: Thu, 30 Sep 2021 23:57:49 +0200 Subject: Add Makefile for downloading and generating datasets --- Makefile | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 Makefile diff --git a/Makefile b/Makefile new file mode 100644 index 0000000..2fb2148 --- /dev/null +++ b/Makefile @@ -0,0 +1,16 @@ +.POSIX: + +download: + poetry run download-emnist + poetry run download-nltk + poetry run download-iam + +generate: + poetry run generate-emnist-lines + poetry run generate-iam-lines + poetry run generate-iam-paragraphs + poetry run generate-iam-synthetic-paragraphs + poetry run extract-iam-text --use_words --save_text train.txt --save_tokens letters.txt + poetry run make-wordpieces --output_prefix iamdb_1kwp --text_file train.txt --num_pieces 1000 + +.PHONY: download generate -- cgit v1.2.3-70-g09d2