{"id":16838473,"url":"https://github.com/olafenwamoses/deepstack_exdark","last_synced_at":"2025-10-07T08:31:36.764Z","repository":{"id":51393212,"uuid":"364577270","full_name":"OlafenwaMoses/DeepStack_ExDark","owner":"OlafenwaMoses","description":"A DeepStack custom model for detecting common objects in dark/night images and videos.","archived":false,"fork":false,"pushed_at":"2021-05-12T08:29:07.000Z","size":1431,"stargazers_count":120,"open_issues_count":4,"forks_count":24,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-01-11T20:40:47.414Z","etag":null,"topics":["ai","cctv","computer-vision","deep-learning","deepstack","machine-learning","night-vision","night-vision-camera","object-detection","yolo","yolov3","yolov5"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/OlafenwaMoses.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}},"created_at":"2021-05-05T12:59:02.000Z","updated_at":"2024-12-28T09:06:49.000Z","dependencies_parsed_at":"2022-09-11T17:22:13.476Z","dependency_job_id":null,"html_url":"https://github.com/OlafenwaMoses/DeepStack_ExDark","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OlafenwaMoses%2FDeepStack_ExDark","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OlafenwaMoses%2FDeepStack_ExDark/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OlafenwaMoses%2FDeepStack_ExDark/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OlafenwaMoses%2FDeepStack_ExDark/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/OlafenwaMoses","download_url":"https://codeload.github.com/OlafenwaMoses/DeepStack_ExDark/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":235607126,"owners_count":19017298,"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":["ai","cctv","computer-vision","deep-learning","deepstack","machine-learning","night-vision","night-vision-camera","object-detection","yolo","yolov3","yolov5"],"created_at":"2024-10-13T12:23:31.787Z","updated_at":"2025-10-07T08:31:31.367Z","avatar_url":"https://github.com/OlafenwaMoses.png","language":"Python","readme":"# DeepStack_ExDark\n\nThis repository provides a custom DeepStack model that has been trained and can be used for creating a new `object detection API` for detecting **12 common objects** (including people) in the **dark/night** images and videos. The Model was trained on the [ExDark dataset](https://github.com/cs-chan/Exclusively-Dark-Image-Dataset) dataset.\n\n\n- **Create API and Detect Objects**\n- **Discover more Custom Models**\n- **Train your own Model**\n\n![](images/1.jpg)\n\n![](images/2.jpg)\n\n![](images/3.jpg)\n\n![](images/4.jpg)\n\n\n\n# Create API and Detect Objects\n\nThe Trained Model can detect the following objects in dark/night images and videos. \n\n- Bicycle\n- Boat\n- Bottle\n- Bus\n- Chair\n- Car\n- Cat\n- Cup \n- Dog\n- Motorbike\n- People\n- Table\n\nTo start detecting, follow the steps below\n\n- **Install DeepStack:** Install DeepStack AI Server with instructions on DeepStack's documentation via [https://docs.deepstack.cc](https://docs.deepstack.cc/index.html#installation)\n- **Download Custom Model:** Download the trained custom model `dark.pt` for ExDark from  [this GitHub release](https://github.com/OlafenwaMoses/DeepStack_ExDark/releases/tag/v1). Create a folder on your machine and move the downloaded model to this folder.\n\n    E.g A path on Windows Machine `C\\Users\\MyUser\\Documents\\DeepStack-Models`, which will make your model file path `C\\Users\\MyUser\\Documents\\DeepStack-Models\\dark.pt`\n\n- **Run DeepStack:** To run DeepStack AI Server with the custom ExDark model, run the command that applies to your machine as detailed on DeepStack's documentation [linked here](https://docs.deepstack.cc/custom-models/deployment/index.html#starting-deepstack).\n\n    E.g\n\n    For a Windows version, you run the command below\n    ```bash\n    deepstack --MODELSTORE-DETECTION \"C\\Users\\MyUser\\Documents\\DeepStack-Models\" --PORT 80\n    ```\n\n    For a Linux machine\n    ```bash\n    sudo docker run -v /home/MyUser/Documents/DeepStack-Models:/modelstore/detection -p 80:5000 deepquestai/deepstack\n    ```\n    Once DeepStack runs, you will see a log like the one below in your `Terminal/Console`\n\n    ![](images/deepstack-log.png)\n\n    That means DeepStack is running your custom `dark.pt` model and now ready to start detecting objects in night/dark images via the API endpoint `http://localhost:80/v1/vision/custom/dark` or `http://your_machine_ip:80/v1/vision/custom/dark`\n\n- **Detect Objects in night image:** You can detect objects in an image by sending a `POST` request to the url mentioned above with the paramater `image` set to an `image` using any proggramming language or with a tool like POSTMAN. For the purpose of this repository, we have provided a sample Python code below.\n\n    - A sample image can be found in `images/image.jpg` of this repository\n\n\n    ![](images/image.jpg)\n\n    - Install Python and install the **DeepStack Python SDK** via the command below\n        ```bash\n        pip install deepstack_sdk\n        ```\n    - Run the Python file `detect.py` in this repository.\n\n        ```bash\n        python detect.py\n        ```\n    - After the code runs, you will find a new image in `images/image_detected.jpg` with the detection visualized, with the following results printed in the Terminal/Console.\n\n        ```\n        Name: People\n        Confidence: 0.74210495\n        x_min: 616\n        x_max: 672\n        y_min: 224\n        y_max: 323\n        -----------------------\n        Name: Dog\n        Confidence: 0.82523036\n        x_min: 250\n        x_max: 327\n        y_min: 288\n        y_max: 349\n        -----------------------\n        Name: Dog\n        Confidence: 0.86660975\n        x_min: 403\n        x_max: 485\n        y_min: 283\n        y_max: 341\n        -----------------------\n        Name: Dog\n        Confidence: 0.87793124\n        x_min: 508\n        x_max: 609\n        y_min: 309\n        y_max: 370\n        -----------------------\n        Name: Dog\n        Confidence: 0.89132285\n        x_min: 286\n        x_max: 372\n        y_min: 316\n        y_max: 393\n        -----------------------\n        ```\n\n        ![](images/image_new.jpg)\n    - You can try running detection for other night/dark images.\n\n# Discover more Custom Models\n\nFor more custom DeepStack models that has been trained and ready to use, visit the Custom Models sample page on DeepStack's documentation [https://docs.deepstack.cc/custom-models-samples/](https://docs.deepstack.cc/custom-models-samples/) .\n\n\n\n# Train your own Model\n\nIf you will like to train a custom model yourself, follow the instructions below.\n\n- **Prepare and Annotate:** Collect images on and annotate object(s) you plan to detect as [ detailed here ](https://docs.deepstack.cc/custom-models/datasetprep/index.html)\n- **Train your Model:** Train the model as [detailed here](https://docs.deepstack.cc/custom-models/training/index.html)","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Folafenwamoses%2Fdeepstack_exdark","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Folafenwamoses%2Fdeepstack_exdark","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Folafenwamoses%2Fdeepstack_exdark/lists"}