{"id":13459558,"url":"https://github.com/Minyus/pipelinex_image_processing","last_synced_at":"2025-03-24T18:30:39.297Z","repository":{"id":106668125,"uuid":"227091829","full_name":"Minyus/pipelinex_image_processing","owner":"Minyus","description":"A project to use PipelineX for image processing","archived":false,"fork":false,"pushed_at":"2020-11-14T07:34:03.000Z","size":448,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-10-29T05:34:50.275Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Minyus.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-12-10T10:34:19.000Z","updated_at":"2023-12-19T20:36:27.000Z","dependencies_parsed_at":null,"dependency_job_id":"4d33232b-623e-44f4-b849-bda1f416b1c5","html_url":"https://github.com/Minyus/pipelinex_image_processing","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":"Minyus/pipelinex_template","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Minyus%2Fpipelinex_image_processing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Minyus%2Fpipelinex_image_processing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Minyus%2Fpipelinex_image_processing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Minyus%2Fpipelinex_image_processing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Minyus","download_url":"https://codeload.github.com/Minyus/pipelinex_image_processing/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245328073,"owners_count":20597352,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-07-31T10:00:19.570Z","updated_at":"2025-03-24T18:30:38.882Z","avatar_url":"https://github.com/Minyus.png","language":"Python","funding_links":[],"categories":["Example projects"],"sub_categories":[],"readme":"# Pipelinex Image Processing\n\nAn example project using [PipelineX](https://github.com/Minyus/pipelinex), Kedro, OpenCV, Scikit-image, and TensorFlow/Keras for image processing.\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"img/kedro_pipeline.PNG\"\u003e\nPipeline visualized by Kedro-viz\n\u003c/p\u003e\n\n## Directories\n\n- `conf`\n  - YAML config files for PipelineX project\n- `data`\n  - empty folders (output files will be saved here)\n- `logs`\n  - empty folders (log files will be saved here)\n- `src`\n  - `empty_area.py`\n    - The algorithm to estimate empty area ratio\n  - `roi.py`\n    - Supplementary algorithm to compute ROI (Region of Interest) from segmentation image\n  - `semantic_segmentation.py`\n    - Semantic segmentation using PSPNet model pretrained with ADE20K dataset\n\n## How to run the code\n\n### 1. Install Python packages\n\n```bash\n$ pip install pipelinex opencv-python scikit-image ocrd-fork-pylsd Pillow pandas numpy requests kedro mlflow kedro-viz\n```\n\nNote: `mlflow` and `kedro-viz` are optional.\n\n#### [Optional] To use the pretrained TensorFlow model:\n\n##### Install tensorflow 1.x and keras-segmentation\n\n```bash\n$ pip install \"tensorflow\u003c2\" keras-segmentation Keras \n```\n\n##### If you want to use TensorFlow 2.x, install fork of keras-segmentation modified to work with TensorFlow 2.x\n\n```bash\n$ pip install \"tensorflow\u003e=2.0.0\" Keras \n$ pip install git+https://github.com/Minyus/image-segmentation-keras.git\n```\n### 2. Clone `https://github.com/Minyus/pipelinex_image_processing.git`\n\n```bash\n$ git clone https://github.com/Minyus/pipelinex_image_processing.git\n$ cd pipelinex_image_processing\n```\n\n### 3. Run `main.py`\n\n```bash\n$ python main.py\n```\n\nAs configured in [catalog.yml](https://github.com/Minyus/pipelinex_image_processing/blob/master/conf/base/catalog.yml), the following 2 images will be downloaded by http requests and then processed using `opencv-python`, `scikit-image`, and `ocrd-fork-pylsd` packages.\n\n![Image](https://cdn.foodlogistics.com/files/base/acbm/fl/image/2018/09/960w/GettyImages_485190815.5b9bfb5550ded.jpg)\n![Image](https://www.thetrailerconnection.com/zupload/library/180/-1279-840x600-0.jpg)\n\n### 4. [Optional] View the experiment logs in MLflow's UI \n\n```bash\n$ mlflow server --host 0.0.0.0 --backend-store-uri sqlite:///mlruns/sqlite.db --default-artifact-root ./mlruns/experiment_001\n```\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"img/mlflow_ui.png\"\u003e\nExperiment logs in MLflow's UI\n\u003c/p\u003e\n\n\n## Tested environment\n\n- Python 3.6.8\n\n\n## Simplified Kedro project template\n\nThis project was created from the GitHub template repository at https://github.com/Minyus/pipelinex_template\n\nTo use for a new project, fork the template repository and hit `Use this template` button next to `Clone or download`.\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://help.github.com/assets/images/help/repository/use-this-template-button.png\"\u003e\n\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMinyus%2Fpipelinex_image_processing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FMinyus%2Fpipelinex_image_processing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMinyus%2Fpipelinex_image_processing/lists"}