{"id":13665741,"url":"https://github.com/rish-16/sight","last_synced_at":"2025-06-26T03:01:57.792Z","repository":{"id":39731672,"uuid":"225373118","full_name":"rish-16/sight","owner":"rish-16","description":"👁 Sightseer: TensorFlow library for state-of-the-art Computer Vision and Object Detection models","archived":false,"fork":false,"pushed_at":"2023-03-24T23:53:50.000Z","size":70001,"stargazers_count":206,"open_issues_count":1,"forks_count":19,"subscribers_count":10,"default_branch":"master","last_synced_at":"2025-05-23T01:16:16.433Z","etag":null,"topics":["computer-vision","object-detection","state-of-the-art","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/rish-16.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":"ROADMAP.md","authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-12-02T12:45:13.000Z","updated_at":"2025-03-03T21:19:47.000Z","dependencies_parsed_at":"2024-11-11T00:42:15.763Z","dependency_job_id":null,"html_url":"https://github.com/rish-16/sight","commit_stats":{"total_commits":138,"total_committers":5,"mean_commits":27.6,"dds":0.08695652173913049,"last_synced_commit":"d04db64a03a5c2808027246b23384ea2e474479c"},"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/rish-16/sight","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rish-16%2Fsight","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rish-16%2Fsight/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rish-16%2Fsight/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rish-16%2Fsight/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rish-16","download_url":"https://codeload.github.com/rish-16/sight/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rish-16%2Fsight/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261518625,"owners_count":23171220,"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":["computer-vision","object-detection","state-of-the-art","tensorflow"],"created_at":"2024-08-02T06:00:49.106Z","updated_at":"2025-06-26T03:01:57.772Z","avatar_url":"https://github.com/rish-16.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n    \u003cbr\u003e\n\t\u003cimg src=\"https://github.com/rish-16/sight/blob/master/Assets/logo.png?raw=true\" width=200\u003e\n    \u003cbr\u003e\n\u003cp\u003e\n\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://pypi.org/project/sightseer/\"\u003e\n        \u003cimg alt=\"PyPI\" src=\"https://img.shields.io/pypi/v/sightseer?color=%231dd1a1\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"https://pepy.tech/project/sightseer\"\u003e\n        \u003cimg alr=\"PyPi - Downloads\" src=\"https://pepy.tech/badge/sightseer\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"https://github.com/rish-16/sight/blob/master/LICENSE\"\u003e\n\t\t\u003cimg alt=\"PyPI - License\" src=\"https://img.shields.io/pypi/l/sightseer?color=%23feca57\"\u003e\n    \u003c/a\u003e\n\u003c/p\u003e\n\n\u003ch3 align=\"center\"\u003e\n\u003cp\u003eState-of-the-art Computer Vision and Object Detection for TensorFlow.\u003c/p\u003e\n\u003c/h3\u003e\n\n\u003ch5 align=\"center\"\u003e\n\u003cp\u003eMade by Rishabh Anand • \u003ca href=\"https://rish-16.github.io\"\u003ehttps://rish-16.github.io\u003c/a\u003e\u003c/p\u003e\n\u003c/h5\u003e\n\n`sightseer` provides state-of-the-art general-purpose architectures (YOLOv3, MaskRCNN, Fast/Faster RCNN, SSD...) for Computer Vision and Object Detection tasks with 30+ pretrained models written in TensorFlow 1.15.\n\n\u003e I'd like to fully credit [Huynh Ngoc Anh](https://github.com/experiencor) for their YOLOv3 model architecture code. I've repackaged that chunk as a callable python API wrapper under the model zoo. This project would not be possible without their contribution.\n\n## Installation\n\n`sightseer` is written in Python 3.5+ and TensorFlow 1.15. \n\nIdeally, `sightseer` should be installed in a [virtual environments](https://docs.python.org/3/library/venv.html). If you're unfamiliar with Python virtual environments, check out this [tutorial](https://packaging.python.org/guides/installing-using-pip-and-virtual-environments/) on getting started.\n\n### Via PyPi\n\nTo use `sightseer`, you must first have TensorFlow installed. To do so, follow the instructions on the [TensorFlow installation page](https://www.tensorflow.org/install/pip?lang=python3).\n\nWhen your virtual environment is set up with TensorFlow, you can install `sightseer` using `pip`:\n\n```bash\npip install sightseer\n```\n\n### Model Clients (as of now)\n\n1. `YOLOv3Client` (Darknet by Joseph Redmon)\n\n\u003e By popular demand, *Tiny YOLO* will be out in the v1.2.0 release. For more information on model release, check out the [Roadmap](https://github.com/rish-16/sight/blob/master/ROADMAP.md).\n\n\n# Components of `sightseer`\n\nThe package comes with 4 major components that help with different parts of the object detection process all the way from preparing your raw data to getting predictions and displaying them.\n\n| Component | Description                                                               |\n|-----------|---------------------------------------------------------------------------|\n| Sightseer | Obtains image data or video footage                                       |\n| Proc      | Provides image/frame-wise annotation and inter-format conversion tools    |\n| Zoo       | Stores the wrappers over all state-of-the-art models and configs          |\n| Serve     | Provides deployment and model serving protocols and services              |\n\nIf not using custom datasets, `Sightseer` and `Zoo` are the submodules majorly used for generic predictions from pre-trained models. When there is custom data involved, you can use `Proc` to annotate your datasets and even convert them between XML/JSON/CSV/TFRecord formats. \n\n\u003e `Serve` is an experimental productionising submodule that helps deploy your models on cloud services like AWS and GCP. For more details on future tools and services, check out the [Roadmap](https://github.com/rish-16/sight/blob/master/ROADMAP.md).\n\n## Features\n\nFootage or raw images can be rendered using `Sightseer` before being ingested into models or further preprocessed.\n\n\u003cstrong\u003e1a. Loading images\u003c/strong\u003e\n\n```python\nfrom sightseer import Sightseer\n\nss = Sightseer()\nimage = ss.load_image(\"path/to/image\") # return numpy array representation of image\n```\n\n\u003cstrong\u003e1b. Loading videos\u003c/strong\u003e\n\n```python\nfrom sightseer import Sightseer\n\nss = Sightseer()\nframes = ss.load_vidsource(\"path/to/video\") # returns nested array of frames\n```\n\n\u003e Support for video, webcam footage, and screen recording will be out in the coming v1.2.0 release.\n\n\u003cstrong\u003e2. Using models from `sightseer.zoo`\u003c/strong\u003e\n\nOnce installed, any model offered by `sightseer` can be accessed in less than 10 lines of code. For instance, the code to use the YOLOv3 (Darknet) model is as follows:\n\n```python\nfrom sightseer import Sightseer\nfrom sightseer.zoo import YOLOv3Client\n\nyolo = YOLOv3Client()\nyolo.load_model() # downloads weights\n\n# loading image from local system\nss = Sightseer()\nimage = ss.load_image(\"./assets/road.jpg\")\n\n# getting labels, confidence scores, and bounding box data\npreds, pred_img = yolo.predict(image, return_img=True)\nss.render_image(pred_img)\n```\n\nTo run the model on frames from a video, you can use the `framewise_predict` method:\n\n```python\nfrom sightseer import Sightseer\nfrom sightseer.zoo import YOLOv3Client\n\nyolo = YOLOv3Client()\nyolo.load_model() # downloads weights\n\n# loading video from local system\nss = Sightseer()\nframes = ss.load_vidsource(\"./assets/video.mp4\")\n\n\"\"\"\nFor best results, run on a GPU\n\"\"\"\n# getting labels, confidence scores, and bounding box data\npreds, pred_frames = yolo.framewise_predict(frames)\nss.render_footage(pred_frames) # plays the video and saves the footage\n```\n\nThe module can even be repurposed into a Command-line Interface (CLI) app using the [`argparse`](https://docs.python.org/3/library/argparse.html) library.\n\n## Contributing\n\nSuggestions, improvements, and enhancements are always welcome! If you have any issues, please do raise one in the Issues section. If you have an improvement, do file an issue to discuss the suggestion before creating a PR.\n\nAll ideas – no matter how outrageous – welcome!\n\nBefore committing, please check the [Roadmap](https://github.com/rish-16/sight/blob/master/ROADMAP.md) to see if proposed features are already in-development or not.\n\n\u003e **Note:** Please commit all changes to the `development` experimentation branch instead of `master`.\n\n## Licence\n\n[Apache Licencse 2.0](https://github.com/rish-16/sight/blob/master/LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frish-16%2Fsight","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frish-16%2Fsight","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frish-16%2Fsight/lists"}