sporada/ocr
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git synced 2025-01-13 17:00:33 +00:00
Code Issues Projects Releases Wiki Activity

Aktualisieren ocr

Browse Source
This commit is contained in:
Patrick Jentsch 2019-04-11 13:51:07 +02:00
parent d4218fcd7c
commit 1e740aec66
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

@ -121,11 +121,12 @@ class OCRWorkflow(WorkflowRunner):
ocropusnlbin_job_number = 0 ocropusnlbin_job_number = 0
for job in self.jobs: for job in self.jobs:
ocropusnlbin_job_number += 1 ocropusnlbin_job_number += 1
cmd = 'ocropus-nlbin -o "%s" "%s"/*' % ( cmd = 'ocropus-nlbin -Q "%i" -o "%s" "%s"/*' % (
max(1, int(self.nCores / length(self.jobs))),
os.path.join(job["output_dir"], "tmp", "ocropus-nlbin"), os.path.join(job["output_dir"], "tmp", "ocropus-nlbin"),
os.path.join(job["output_dir"], "tmp", "tiff_files") os.path.join(job["output_dir"], "tmp", "tiff_files")
) )
ocropusnlbin_jobs.append(self.addTask(label="ocropusnlbin_job_-_%i" % (ocropusnlbin_job_number), command=cmd, dependencies=split_jobs, nCores=max(1, self.nCores / length(self.jobs))) ocropusnlbin_jobs.append(self.addTask(label="ocropusnlbin_job_-_%i" % (ocropusnlbin_job_number), command=cmd, dependencies=split_jobs, nCores=max(1, int(self.nCores / length(self.jobs)))))
### ###
# Task "tesseract_job": perform OCR on binarized images # Task "tesseract_job": perform OCR on binarized images