sporada/ocr
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git synced 2025-02-28 16:34:49 +00:00
Code Issues Projects Releases Wiki Activity

Use a single core for deu_frak

Browse Source
This commit is contained in:
Patrick Jentsch 2019-04-15 09:56:47 +02:00
parent d84db585fa
commit fdc53fd16c
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
ocr
View File

@ -172,9 +172,10 @@ class OCRWorkflow(WorkflowRunner):
''' '''
' Tesseract runs fastest with four cores. So we run it with either four ' Tesseract runs fastest with four cores. So we run it with either four
' or, if there are less then four cores available for this workflow, the ' or, if there are less then four cores available for this workflow, the
' available core number. ' available core number. The deu_frak language model only supports
' single core processing, so we use use only one core for this language.
''' '''
ocr_job_nCores = min(4, self.nCores) ocr_job_nCores = 1 if self.lang == "deu_frak" else min(4, self.nCores)
for job in self.jobs: for job in self.jobs:
for file in filter(lambda x: x.endswith(".tif") if self.skipBinarization else x.endswith(".bin.png"), os.listdir(os.path.join(job["output_dir"], "tmp"))): for file in filter(lambda x: x.endswith(".tif") if self.skipBinarization else x.endswith(".bin.png"), os.listdir(os.path.join(job["output_dir"], "tmp"))):
ocr_job_number += 1 ocr_job_number += 1