2025-04-05 12:34:21 +00:00
9 changed files with 755 additions and 968 deletions
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@ -1,68 +1,44 @@
-image: docker:19.03.13
+image: docker:stable

 services:
-  - docker:19.03.13-dind
+  - docker:stable-dind
+
+variables:
+  DOCKER_DRIVER: overlay2

 stages:
  - build
  - push

-variables:
-  DOCKER_TLS_CERTDIR: "/certs"
-  INTERMEDIATE_IMAGE_TAG: $CI_REGISTRY_IMAGE:$CI_COMMIT_REF_NAME-$CI_COMMIT_SHA
+before_script:
+  - docker login -u gitlab-ci-token -p $CI_JOB_TOKEN $CI_REGISTRY

-.reg_setup:
-  before_script:
-    - apk add --no-cache curl
-    - curl --fail --show-error --location "https://github.com/genuinetools/reg/releases/download/v$REG_VERSION/reg-linux-amd64" --output /usr/local/bin/reg
-    - echo "$REG_SHA256  /usr/local/bin/reg" | sha256sum -c -
-    - chmod a+x /usr/local/bin/reg
-  variables:
-    REG_SHA256: ade837fc5224acd8c34732bf54a94f579b47851cc6a7fd5899a98386b782e228
-    REG_VERSION: 0.16.1
-
-build_image:
+Build:
  script:
-    - docker login -u gitlab-ci-token -p $CI_JOB_TOKEN $CI_REGISTRY
-    - docker build -t $INTERMEDIATE_IMAGE_TAG .
-    - docker push $INTERMEDIATE_IMAGE_TAG
+    - docker build --pull -t $CI_REGISTRY_IMAGE:tmp .
+    - docker push $CI_REGISTRY_IMAGE:tmp
  stage: build
  tags:
-    - docker
+  - docker

-push_master:
-  extends:
-    - .reg_setup
+Push latest:
  only:
    - master
  script:
-    - docker login -u gitlab-ci-token -p $CI_JOB_TOKEN $CI_REGISTRY
-    - docker pull $INTERMEDIATE_IMAGE_TAG
-    - /usr/local/bin/reg rm -d --auth-url $CI_REGISTRY -u $CI_REGISTRY_USER -p $CI_REGISTRY_PASSWORD $INTERMEDIATE_IMAGE_TAG
-    - docker tag $INTERMEDIATE_IMAGE_TAG $IMAGE_TAG
-    - docker push $IMAGE_TAG
+    - docker pull $CI_REGISTRY_IMAGE:tmp
+    - docker tag $CI_REGISTRY_IMAGE:tmp $CI_REGISTRY_IMAGE:latest
+    - docker push $CI_REGISTRY_IMAGE:latest
  stage: push
  tags:
-    - docker
-  variables:
-    IMAGE_TAG: $CI_REGISTRY_IMAGE:latest
+  - docker

-push_other:
-  extends:
-    - .reg_setup
-  except:
-    - master
+Push tag:
  only:
-    - branches
    - tags
  script:
-    - docker login -u gitlab-ci-token -p $CI_JOB_TOKEN $CI_REGISTRY
-    - docker pull $INTERMEDIATE_IMAGE_TAG
-    - /usr/local/bin/reg rm -d --auth-url $CI_REGISTRY -u $CI_REGISTRY_USER -p $CI_REGISTRY_PASSWORD $INTERMEDIATE_IMAGE_TAG
-    - docker tag $INTERMEDIATE_IMAGE_TAG $IMAGE_TAG
-    - docker push $IMAGE_TAG
+    - docker pull $CI_REGISTRY_IMAGE:tmp
+    - docker tag $CI_REGISTRY_IMAGE:tmp $CI_REGISTRY_IMAGE:$CI_COMMIT_REF_NAME
+    - docker push $CI_REGISTRY_IMAGE:$CI_COMMIT_REF_NAME
  stage: push
  tags:
-    - docker
-  variables:
-    IMAGE_TAG: $CI_REGISTRY_IMAGE:$CI_COMMIT_REF_NAME
+  - docker
--- a/116
+++ b/116
@ -1,85 +1,73 @@
-FROM debian:buster-slim
+FROM debian:9-slim


-LABEL authors="Patrick Jentsch <p.jentsch@uni-bielefeld.de>, Stephan Porada <porada@posteo.de>"
+# Define image metadata
+LABEL maintainer="inf_sfb1288@lists.uni-bielefeld.de"


 ENV LANG=C.UTF-8


+# Install prerequisites
 RUN apt-get update \
- && apt-get install --no-install-recommends --yes \
-      ghostscript \
-      procps \
-      python3.7 \
-      python3-pip \
-      rename \
+ && apt-get install -y --no-install-recommends \
+      apt-transport-https \
+      ca-certificates \
+      gnupg2 \
+      imagemagick \
+      poppler-utils \
+      python2.7 \
+      python3.5 \
      wget \
      zip \
- && python3 -m pip install lxml
+ && rm -rf /var/lib/apt/lists/*

-# Install the OCR pipeline and it's dependencies #
-## Install pyFlow ##
-ENV PYFLOW_VERSION=1.1.20
-RUN wget --no-check-certificate --quiet \
-      "https://github.com/Illumina/pyflow/releases/download/v${PYFLOW_VERSION}/pyflow-${PYFLOW_VERSION}.tar.gz" \
- && tar -xzf "pyflow-${PYFLOW_VERSION}.tar.gz" \
- && cd "pyflow-${PYFLOW_VERSION}" \
- && apt-get install --no-install-recommends --yes \
-      python2.7 \
- && python2.7 setup.py build install \
- && cd - > /dev/null \
- && rm -r "pyflow-${PYFLOW_VERSION}" "pyflow-${PYFLOW_VERSION}.tar.gz"
-
-
-## Install ocropy ##
-ENV OCROPY_VERSION=1.3.3
-RUN wget --no-check-certificate --quiet \
-      "https://github.com/tmbdev/ocropy/archive/v${OCROPY_VERSION}.tar.gz" \
- && tar -xzf "v${OCROPY_VERSION}.tar.gz" \
+ENV OCROPY_VERSION 1.3.3
+ADD "https://github.com/tmbdev/ocropy/archive/v${OCROPY_VERSION}.tar.gz" .
+RUN tar -xzf "v${OCROPY_VERSION}.tar.gz" \
 && cd "ocropy-${OCROPY_VERSION}" \
- && apt-get install --no-install-recommends --yes \
-      python2.7 \
+ && apt-get update \
+ && apt-get install -y --no-install-recommends \
      python-pil \
      python-tk \
      $(cat PACKAGES) \
+ && rm -rf /var/lib/apt/lists/* \
 && python2.7 setup.py install \
- && cd - > /dev/null \
- && rm -r "ocropy-${OCROPY_VERSION}" "v${OCROPY_VERSION}.tar.gz"
+ && cd .. \
+ && rm -rf \
+      "ocropy-${OCROPY_VERSION}" \
+      "v${OCROPY_VERSION}.tar.gz"
+
+ENV PYFLOW_VERSION=1.1.20
+ADD "https://github.com/Illumina/pyflow/releases/download/v${PYFLOW_VERSION}/pyflow-${PYFLOW_VERSION}.tar.gz" .
+RUN tar -xzf "pyflow-${PYFLOW_VERSION}.tar.gz" \
+ && cd "pyflow-${PYFLOW_VERSION}" \
+ && python2.7 setup.py build install \
+ && cd .. \
+ && rm -rf \
+      "pyflow-${PYFLOW_VERSION}" \
+      "pyflow-${PYFLOW_VERSION}.tar.gz"
+
+RUN echo "deb https://notesalexp.org/tesseract-ocr/stretch/ stretch main" >> /etc/apt/sources.list \
+ && wget -O - https://notesalexp.org/debian/alexp_key.asc | apt-key add - \
+ && apt-get update \
+ && apt-get install -y --no-install-recommends \
+      tesseract-ocr  \
+      tesseract-ocr-deu \
+      tesseract-ocr-eng \
+      tesseract-ocr-enm \
+      tesseract-ocr-fra \
+      tesseract-ocr-frk \
+      tesseract-ocr-frm \
+      tesseract-ocr-ita \
+      tesseract-ocr-por \
+      tesseract-ocr-spa \
+ && rm -rf /var/lib/apt/lists/*


-## Install Tesseract OCR ##
-ENV TESSERACT_VERSION=5.0.0
-RUN wget --no-check-certificate --quiet \
-      "https://github.com/tesseract-ocr/tesseract/archive/${TESSERACT_VERSION}.tar.gz" \
- && tar -xzf "${TESSERACT_VERSION}.tar.gz" \
- && cd "tesseract-${TESSERACT_VERSION}" \
- && apt-get install --no-install-recommends --yes \
-      autoconf \
-      automake \
-      g++ \
-      libjpeg62-turbo-dev \
-      libleptonica-dev \
-      libtiff5-dev \
-      libtool \
-      libpng-dev \
-      make \
-      pkg-config \
-      zlib1g-dev \
- && ./autogen.sh \
- && ./configure --disable-openmp --disable-shared 'CXXFLAGS=-g -O2 -fno-math-errno -Wall -Wextra -Wpedantic' \
- && make \
- && make install \
- && ldconfig \
- && cd - > /dev/null \
- && rm -r "tesseract-${TESSERACT_VERSION}" "${TESSERACT_VERSION}.tar.gz"
-
-
-RUN rm -r /var/lib/apt/lists/*
-
-
-## Install Pipeline ##
-COPY hocr2tei hocr-combine ocr /usr/local/bin/
+# Install OCR pipeline
+COPY hocrtotei /usr/local/bin
+COPY ocr /usr/local/bin


 ENTRYPOINT ["ocr"]
--- a/21
+++ b/21
@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2021 Bielefeld University - CRC 1288 - INF
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
--- a/README.md
+++ b/README.md
@ -1,49 +1,96 @@
-# OCR - Optical Character Recognition
+# OCR

-This software implements a heavily parallelized pipeline to recognize text in PDF files. It is used for nopaque's OCR service but you can also use it standalone, for that purpose a convenient wrapper script is provided. The pipeline is designed to run on Linux operating systems, but with some tweaks it should also run on Windows with WSL installed.
+## Build image

-## Software used in this pipeline implementation
-
- Official Debian Docker image (buster-slim): https://hub.docker.com/_/debian
-  - Software from Debian Buster's free repositories
- ocropy (1.3.3): https://github.com/ocropus/ocropy/releases/tag/v1.3.3
- pyFlow (1.1.20): https://github.com/Illumina/pyflow/releases/tag/v1.1.20
- Tesseract OCR (5.0.0): https://github.com/tesseract-ocr/tesseract/releases/tag/5.0.0
-
-## Installation
-
-1. Install Docker and Python 3.
-2. Clone this repository: `git clone https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git`
-3. Build the Docker image: `docker build -t gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/ocr:v0.1.0 ocr`
-4. Add the wrapper script (`wrapper/ocr` relative to this README file) to your `${PATH}`.
-5. Create working directories for the pipeline: `mkdir -p /<my_data_location>/{input,models,output}`.
-6. Place your Tesseract OCR model(s) inside `/<my_data_location>/models`.
-
-## Use the Pipeline
-
-1. Place your PDF files inside `/<my_data_location>/input`. Files should all contain text of the same language.
-2. Clear your `/<my_data_location>/output` directory.
-3. Start the pipeline process. Check the pipeline help (`ocr --help`) for more details.
-```bash
-cd /<my_data_location>
-# <model_code> is the model filename without the ".traineddata" suffix
-ocr \
-  --input-dir input \
-  --output-dir output \
-  --model-file models/<model>
-  -m <model_code> <optional_pipeline_arguments>
-# More then one model
-ocr \
-  --input-dir input \
-  --output-dir output \
-  --model-file models/<model1>
-  --model-file models/<model2>
-  -m <model1_code>+<model2_code> <optional_pipeline_arguments>
-# Instead of multiple --model-file statements, you can also use
-ocr \
-  --input-dir input \
-  --output-dir output \
-  --model-file models/*
-  -m <model1_code>+<model2_code> <optional_pipeline_arguments>
+1. Clone this repository and navigate into it:
+```
+git clone https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git && cd ocr
+```
+
+2. Build image:
+```
+docker build -t sfb1288inf/ocr:latest .
+```
+
+Alternatively build from the GitLab repository without cloning:
+
+1. Build image:
+```
+docker build -t sfb1288inf/ocr:latest https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git
+```
+
+## Download prebuilt image
+
+The GitLab registry provides a prebuilt image. It is automatically created, utilizing the conquaire build servers.
+
+1. Download image:
+```
+docker pull gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/ocr:latest
+```
+
+## Run
+
+1. Create input and output directories for the OCR software:
+```
+mkdir -p /<mydatalocation>/files_for_ocr /<mydatalocation>/files_from_ocr
+```
+
+2. Place your files inside the `/<mydatalocation>/files_for_ocr` directory. Files can either be PDF (.pdf) or multipage TIFF (.tiff, .tif) files. Files should all contain text of the same language.
+
+3. Start the OCR process.
+```
+docker run \
+    --rm \
+    -it \
+    -u $(id -u $USER):$(id -g $USER) \
+    -v /<mydatalocation>/files_for_ocr:/input \
+    -v /<mydatalocation>/files_from_ocr:/output \
+    sfb1288inf/ocr:latest \
+        -i /input \
+        -l <languagecode> \
+        -o /output
+```
+The arguments below `sfb1288inf/ocr:latest` are described in the [OCR arguments](#ocr-arguments) part.
+
+If you want to use the prebuilt image, replace `sfb1288inf/ocr:latest` with `gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/ocr:latest`.
+
+4. Check your results in the `/<mydatalocation>/files_from_ocr` directory.
+
+### OCR arguments
+
+`-l languagecode`
+* Tells tesseract which language will be used.
+* options = deu (German), eng (English), enm (Middle englisch), fra (French), frk (German Fraktur), frm (Middle french), ita (Italian), por (Portuguese), spa (Spanish)
+* required = True
+
+`--keep-intermediates`
+* If set, all intermediate files created during the OCR process will be
+kept.
+* default = False
+* required = False
+
+`--nCores corenumber`
+* Sets the number of CPU cores being used during the OCR process.
+* default = min(4, multiprocessing.cpu_count())
+* required = False
+
+`--skip-binarisation`
+* Used to skip binarization with ocropus. If skipped, only the tesseract binarization is used.
+* default = False
+
+Example with all arguments used:
+```
+docker run \
+    --rm \
+    -it \
+    -u $(id -u $USER):$(id -g $USER) \
+    -v "$HOME"/ocr/files_for_ocr:/input \
+    -v "$HOME"/ocr/files_from_ocr:/output \
+    sfb1288inf/ocr:latest \
+        -i /input \
+        -l eng \
+        -o /output \
+        --keep_intermediates \
+        --nCores 8 \
+        --skip-binarisation
 ```
-4. Check your results in the `/<my_data_location>/output` directory.
--- a/44
+++ b/44
@ -1,44 +0,0 @@
-#!/usr/bin/env python3.7
-# coding=utf-8
-
-''' Combine multiple hOCR files. '''
-
-from argparse import ArgumentParser
-from lxml import html
-
-
-parser = ArgumentParser(description='Combine multiple hOCR files.')
-parser.add_argument(
-    '-i', '--input-file',
-    help='Input file',
-    nargs='+',
-    required=True
-)
-parser.add_argument(
-    '-o', '--output-file',
-    help='Output file',
-    required=True
-)
-args = parser.parse_args()
-
-
-for input_file in args.input_file:
-    input_files = []
-    if input_file.startswith('@'):
-        with open(input_file[1:], 'r') as f:
-            input_files += [x for x in f.read().split("\n") if x != '']
-    else:
-        input_files.append(input_file)
-if len(input_files) == 0:
-    exit(1)
-
-
-hocr = html.parse(input_files[0])
-hocr_body = hocr.find('body')
-for input_file in input_files[1:]:
-    for ocr_page in html.parse(input_file).findall('//div[@class="ocr_page"]'):
-        hocr_body.append(ocr_page)
-
-
-with open(args.output_file, 'wb') as f:
-    hocr.write(f, encoding='UTF-8', method='html')
--- a/68
+++ b/68
@ -1,68 +0,0 @@
-#!/usr/bin/env python3.7
-# coding=utf-8
-
-''' Convert hOCR to TEI XML. '''
-
-from argparse import ArgumentParser
-from lxml import html
-from xml.sax.saxutils import escape
-import re
-
-
-parser = ArgumentParser(description='Convert hOCR to TEI XML.')
-parser.add_argument(
-    '-i', '--input-file',
-    help='Input file',
-    required=True
-)
-parser.add_argument(
-    '-o', '--output-file',
-    help='Output file',
-    required=True
-)
-args = parser.parse_args()
-
-
-tei = ''
-tei += '<TEI xmlns="http://www.tei-c.org/ns/1.0">\n'
-tei += '  <teiHeader>\n'
-tei += '    <fileDesc>\n'
-tei += '      <titleStmt>\n'
-tei += '        <title></title>\n'
-tei += '      </titleStmt>\n'
-tei += '      <publicationStmt>\n'
-tei += '        <p></p>\n'
-tei += '      </publicationStmt>\n'
-tei += '      <sourceDesc>\n'
-tei += '        <p></p>\n'
-tei += '      </sourceDesc>\n'
-tei += '    </fileDesc>\n'
-tei += '  </teiHeader>\n'
-tei += '  <text>\n'
-tei += '    <body>\n'
-hocr = html.parse(args.input_file)
-for ocr_page in hocr.findall('.//div[@class="ocr_page"]'):
-    ocr_page_title_attrib = ocr_page.attrib.get('title')
-    facsimile = re.search(r'image \"(.*?)\"', ocr_page_title_attrib).group(1)
-    page_number = re.search(r'ppageno (\d+)', ocr_page_title_attrib).group(1)
-    tei += f'      <pb facs="{facsimile}" n="{page_number}"/>\n'
-    for ocr_par in ocr_page.findall('.//p[@class="ocr_par"]'):
-        tei += '      <p>\n'
-        for ocr_line in ocr_par.findall('.//span[@class="ocr_line"]'):
-            tei += '        <lb/>'
-            is_first_word_in_line = True
-            for ocrx_word in ocr_line.findall('.//span[@class="ocrx_word"]'):
-                if ocrx_word.text is not None:
-                    if not is_first_word_in_line:
-                        tei += ' '
-                    tei += escape(ocrx_word.text)
-                    is_first_word_in_line = False
-            tei += '\n'
-        tei += '      </p>\n'
-tei += '    </body>\n'
-tei += '  </text>\n'
-tei += '</TEI>\n'
-
-
-with open(args.output_file, 'w') as f:
-    f.write(tei)
--- a/58
+++ b/58
@ -0,0 +1,58 @@
+#!/usr/bin/env python3.5
+# coding=utf-8
+
+from xml.sax.saxutils import escape
+import argparse
+import xml.etree.ElementTree as ET
+
+parser = argparse.ArgumentParser(
+    description='Merges several hOCR files in order of their occurrence on command line to one TEI result file.'
+)
+parser.add_argument(
+    'i',
+    metavar='hOCR-sourcefile',
+    nargs='+'
+)
+parser.add_argument(
+    'o',
+    metavar='TEI-destfile',
+)
+args = parser.parse_args()
+
+output_file = open(args.o, 'w')
+
+output_file.write(
+      '<?xml version="1.0" encoding="UTF-8"?>\n'
+    + '<TEI xmlns="http://www.tei-c.org/ns/1.0" xml:id="dtabf">\n'
+    + '    <teiHeader>\n'
+    + '        <fileDesc>\n'
+    + '            <titleStmt/>\n'
+    + '            <publicationStmt/>\n'
+    + '            <sourceDesc/>\n'
+    + '        </fileDesc>\n'
+    + '        <encodingDesc/>\n'
+    + '        <profileDesc/>\n'
+    + '    </teiHeader>\n'
+    + '    <text>\n'
+    + '        <body>\n'
+)
+for index, input_file in enumerate(args.i):
+    tree = ET.parse(input_file)
+    output_file.write('            <pb n="%i"/>\n' % (index + 1))
+    for para in tree.findall('.//*[@class="ocr_par"]'):
+        output_file.write('            <p>\n')
+        for line in para.findall('.//*[@class="ocr_line"]'):
+            first_word_in_line = True
+            for word in line.findall('.//*[@class="ocrx_word"]'):
+                if word.text is not None:
+                    output_file.write(('                ' if first_word_in_line else ' ') + escape(word.text.strip()))
+                    first_word_in_line = False
+            if not first_word_in_line:
+                output_file.write('<lb/>\n')
+        output_file.write('            </p>\n')
+output_file.write(
+      '        </body>\n'
+    + '    </text>\n'
+    + '</TEI>')
+
+output_file.close()
--- a/1154
+++ b/1154
--- a/wrapper/ocr
+++ b/wrapper/ocr
@ -1,44 +1,39 @@
 #!/usr/bin/env python3
 # coding=utf-8

-from argparse import ArgumentParser
+import argparse
 import os
 import subprocess
-import sys

-CONTAINER_IMAGE = 'gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/ocr:v0.1.0'
-CONTAINER_INPUT_DIR = '/input'
-CONTAINER_OUTPUT_DIR = '/output'
-CONTAINER_MODELS_DIR = '/usr/local/share/tessdata'
-CONTAINER_LOG_DIR = '/logs'
-UID = str(os.getuid())
-GID = str(os.getgid())
+container_image = 'gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/ocr:latest'
+container_input_dir = '/input'
+container_output_dir = '/output'
+uid = str(os.getuid())
+gid = str(os.getgid())

-parser = ArgumentParser(add_help=False)
-parser.add_argument('-i', '--input-dir')
-parser.add_argument('-o', '--output-dir')
-parser.add_argument('-t', '--model-file', action='extend', nargs='+')
-parser.add_argument('--log-dir')
+parser = argparse.ArgumentParser(add_help=False)
+parser.add_argument(
+    '-i',
+    dest='input_dir',
+    required=False
+)
+parser.add_argument(
+    '-o',
+    dest='output_dir',
+    required=False
+)
 args, remaining_args = parser.parse_known_args()

-cmd = ['docker', 'run', '--rm', '-it', '-u', f'{UID}:{GID}']
+cmd = ['docker', 'run', '--rm', '-it', '-u', uid + ':' + gid]
 if args.input_dir is not None:
-    mapping = f'{os.path.abspath(args.input_dir)}:{CONTAINER_INPUT_DIR}'
-    cmd += ['-v', mapping]
-    remaining_args += ['-i', CONTAINER_INPUT_DIR]
+    host_input_dir = os.path.abspath(args.input_dir)
+    cmd += ['-v', host_input_dir + ':' + container_input_dir]
+    remaining_args += ['-i', container_input_dir]
 if args.output_dir is not None:
-    mapping = f'{os.path.abspath(args.output_dir)}:{CONTAINER_OUTPUT_DIR}'
-    cmd += ['-v', mapping]
-    remaining_args += ['-o', CONTAINER_OUTPUT_DIR]
-if args.model_file is not None:
-    for model_file in args.model_file:
-        mapping = f'{os.path.abspath(model_file)}:{CONTAINER_MODELS_DIR}/{os.path.basename(model_file)}'  # noqa
-        cmd += ['-v', mapping]
-if args.log_dir is not None:
-    mapping = '{os.path.abspath(args.log_dir)}:{CONTAINER_LOG_DIR}'
-    cmd += ['-v', mapping]
-    remaining_args += ['--log-dir', CONTAINER_LOG_DIR]
-cmd.append(CONTAINER_IMAGE)
+    host_output_dir = os.path.abspath(args.output_dir)
+    cmd += ['-v', host_output_dir + ':' + container_output_dir]
+    remaining_args += ['-o', container_output_dir]
+cmd.append(container_image)
 cmd += remaining_args

-sys.exit(subprocess.run(cmd).returncode)
+subprocess.run(cmd)