{"id":19233197,"url":"https://github.com/vdvpie22/invoice_area_detection","last_synced_at":"2026-06-23T09:31:51.052Z","repository":{"id":197788203,"uuid":"309950309","full_name":"vdvpie22/invoice_area_detection","owner":"vdvpie22","description":null,"archived":false,"fork":false,"pushed_at":"2020-11-04T09:09:22.000Z","size":3538,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-23T11:41:59.718Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/vdvpie22.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}},"created_at":"2020-11-04T09:07:34.000Z","updated_at":"2020-11-04T09:09:25.000Z","dependencies_parsed_at":"2023-10-02T16:18:13.289Z","dependency_job_id":null,"html_url":"https://github.com/vdvpie22/invoice_area_detection","commit_stats":null,"previous_names":["vdvpie22/invoice_area_detection"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/vdvpie22/invoice_area_detection","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vdvpie22%2Finvoice_area_detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vdvpie22%2Finvoice_area_detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vdvpie22%2Finvoice_area_detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vdvpie22%2Finvoice_area_detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vdvpie22","download_url":"https://codeload.github.com/vdvpie22/invoice_area_detection/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vdvpie22%2Finvoice_area_detection/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34684673,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-23T02:00:07.161Z","response_time":65,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":"2024-11-09T16:09:18.967Z","updated_at":"2026-06-23T09:31:51.021Z","avatar_url":"https://github.com/vdvpie22.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# [How to train an object detection model easy for free](https://www.dlology.com/blog/how-to-train-an-object-detection-model-easy-for-free/) | DLology Blog\n\n\n\n## How to Run\n\nEasy way: run [this Colab Notebook](https://colab.research.google.com/github/Tony607/object_detection_demo/blob/master/tensorflow_object_detection_training_colab.ipynb).\n\nAlternatively, if you want to use your images instead of ones comes with this repo.\n\nRequire [Python 3.5+](https://www.python.org/ftp/python/3.6.4/python-3.6.4.exe) installed.\n### Fork and clone this repository to your local machine.\n```\nhttps://github.com/Tony607/object_detection_demo\n```\n### Install required libraries\n`pip3 install -r requirements.txt`\n\n\n### Step 1: Annotate some images\n- Save some photos with your custom object(s), ideally with `jpg` extension to `./data/raw` directory. (If your objects are simple like ones come with this repo, 20 images can be enough.)\n- Resize those photo to uniformed size. e.g. `(800, 600)` with\n```\npython resize_images.py --raw-dir ./data/raw --save-dir ./data/images --ext jpg --target-size \"(800, 600)\"\n```\nResized images locate in `./data/images/`\n- Train/test split those files into two directories, `./data/images/train` and `./data/images/test`\n\n- Annotate resized images with [labelImg](https://tzutalin.github.io/labelImg/), generate `xml` files inside `./data/images/train` and `./data/images/test` folders. \n\n*Tips: use shortcuts (`w`: draw box, `d`: next file, `a`: previous file, etc.) to accelerate the annotation.*\n\n- Commit and push your annotated images and xml files (`./data/images/train` and `./data/images/test`) to your forked repository.\n\n\n### Step 2: Open [Colab notebook](https://colab.research.google.com/github/Tony607/object_detection_demo/blob/master/tensorflow_object_detection_training_colab.ipynb)\n- Replace the repository's url to yours and run it.\n\n\n## How to run inference on frozen TensorFlow graph\n\nRequirements:\n- `frozen_inference_graph.pb` Frozen TensorFlow object detection model downloaded from Colab after training. \n- `label_map.pbtxt` File used to map correct name for predicted class index downloaded from Colab after training.\n\nYou can also opt to download my [copy](https://github.com/Tony607/object_detection_demo/releases/download/V0.1/checkpoint.zip) of those files from the GitHub Release page.\n\n\nRun the following Jupyter notebook locally.\n```\nlocal_inference_test.ipynb\n```\n# [How to run TensorFlow object detection model faster with Intel Graphics](https://www.dlology.com/blog/how-to-run-tensorflow-object-detection-model-faster-with-intel-graphics/) | DLology Blog\n\n## How to deploy the trained custom object detection model with OpenVINO\n\nRequirements:\n- Frozen TensorFlow object detection model. i.e. `frozen_inference_graph.pb` downloaded from Colab after training.\n- The modified pipeline config file used for training. Also downloaded from Colab after training.\n\nYou can also opt to download my [copy](https://github.com/Tony607/object_detection_demo/releases/download/V0.1/checkpoint.zip) of those files from the GitHub Release page.\n\nRun the following Jupyter notebook locally and follow the instructions in side.\n```\ndeploy/openvino_convert_tf_object_detection.ipynb\n```\n## Run the benchmark\n\nExamples\n\nBenchmark SSD mobileNet V2 on GPU with FP16 quantized weights.\n```\ncd ./deploy\npython openvino_inference_benchmark.py\\\n     --model-dir ./models/ssd_mobilenet_v2_custom_trained/FP16\\\n     --device GPU\\\n     --data-type FP16\\\n     --img ../test/15.jpg\n```\nTensorFlow benchmark on cpu\n```\npython local_inference_test.py\\\n     --model ./models/frozen_inference_graph.pb\\\n     --img ./test/15.jpg\\\n     --cpu\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvdvpie22%2Finvoice_area_detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvdvpie22%2Finvoice_area_detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvdvpie22%2Finvoice_area_detection/lists"}