initial commit

Author: jackie930

.gitignore

@@ -0,0 +1,130 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+.DS_Store

README.md

@@ -1,11 +1,28 @@
-## My Project
+##  train-and-deploy-ocr-model-on-amazon-sagemaker
 
-TODO: Fill this README out!
+**Onboard PaddleOCR with SageMaker Projects for MLOps, illustration with optical character recognition on identity documents**
 
-Be sure to:
+# Quick Start 
+
+run train_and_deploy/notebook.ipynb
+
+# code repo organisation (proposition) 
+
+* experiments-sagemaker-studio (container will be built through CICD)
+* experiments-notebooks (container will be built with docker build, test with local mode)
+* image-build-train
+* image-build-deploy
+* sagemaker-pipeline-workflow
+
+## Features
+
+- [x] **SageMaker Training/Deploy BYOC Mode Support**
+- [x] **BYOC training support integrate with Amazon SageMaker training hyper-parameters**
+- [x] **convert models from training for inference**
+- [x] **BYOC inference support S3ModelURL**
+- [ ] **onnx speed up**
+- [ ] **integrate with Amazon SageMaker pipeline**
 
-* Change the title in this README
-* Edit your repository description on GitHub
 
 ## Security
 

experiments-sagemaker-studio/input/data/rec_gt_test.txt

@@ -0,0 +1,3 @@
+test/0.jpg	高雄醫學大學附設中和紀念醫院
+test/1.jpg	佛教慈濟醫療財團法人花蓮慈濟醫院
+test/2.jpg	基督復臨安息日會醫療財團法人臺

experiments-sagemaker-studio/input/data/rec_gt_train.txt

@@ -0,0 +1,16 @@
+train/0.jpg	國立臺灣大學醫學院附設醫院
+train/1.jpg	三軍總醫院
+train/2.jpg	臺北榮民總醫院
+train/3.jpg	國泰綜合醫院
+train/4.jpg	臺北及林口長庚醫院
+train/5.jpg	馬偕紀念醫院
+train/6.jpg	新光吳火獅紀念醫院
+train/7.jpg	臺北市立萬芳醫院
+train/8.jpg	亞東紀念醫院
+train/9.jpg	臺中榮民總醫院
+train/10.jpg	中山醫學大學附設醫院
+train/11.jpg	中國醫藥大學附設醫院
+train/12.jpg	彰化基督教醫療財團法人彰化基督教醫院
+train/13.jpg	國立成功大學醫學院附設醫院
+train/14.jpg	奇美醫院
+train/15.jpg	高雄榮民總醫院

experiments-sagemaker-studio/input/data/test/0.jpg

@@ -0,0 +1,3 @@
+0.jpg 高雄醫學大學附設中和紀念醫院
+1.jpg 佛教慈濟醫療財團法人花蓮慈濟醫院
+2.jpg 基督復臨安息日會醫療財團法人臺