{"id":21441195,"url":"https://github.com/europa502/cds","last_synced_at":"2026-04-16T08:33:11.686Z","repository":{"id":217134238,"uuid":"173543107","full_name":"europa502/CDS","owner":"europa502","description":"Content Detection System - Dectecting the occerance of objects in a movie/video.","archived":false,"fork":false,"pushed_at":"2019-03-20T04:35:38.000Z","size":40,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-23T10:25:24.830Z","etag":null,"topics":["opencv","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/europa502.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}},"created_at":"2019-03-03T07:14:33.000Z","updated_at":"2020-02-23T16:47:58.000Z","dependencies_parsed_at":"2024-01-14T20:01:58.873Z","dependency_job_id":null,"html_url":"https://github.com/europa502/CDS","commit_stats":null,"previous_names":["europa502/cds"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/europa502%2FCDS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/europa502%2FCDS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/europa502%2FCDS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/europa502%2FCDS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/europa502","download_url":"https://codeload.github.com/europa502/CDS/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243955750,"owners_count":20374372,"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":["opencv","tensorflow"],"created_at":"2024-11-23T01:21:48.542Z","updated_at":"2026-04-16T08:33:06.664Z","avatar_url":"https://github.com/europa502.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# Content Detection System\n\n\nThis program is made to detect specific contents from video files. Currently it just detects objects from video frames only.\n\n\n## Prerequisites- \n\n1. Python 2.7\n2. Python libraries - Tensorflow, OpenCV.\n3. Video file for testing the model.\n\n### 1. Collect dataset- \n  Download images that represent each category. At least two categories are required to train your model initially. More\n  the images, the better. But make sure that only relevent images with charecterstic features are present. Otherwise it may reduce \n  the accureacy of the model.\n  For this purpose you can use batch downloader extentions for your browsers.\n  Sort these images into respective folders.\n  ![screenshot from 2019-03-03 09-35-39](https://user-images.githubusercontent.com/26405791/53693395-ca9aa800-3d97-11e9-86fd-7902ad50355b.png)\n\n\n### 2. Train your model-\n  Run trainer.py to train develop your model.\n  ```\n  root@europa:~# python trainer.py --bottleneck_dir bottlenecks/ --image_dir training_set/ --output_labels CDS_output_labels.txt \n  --output_graph CDS_output_graph.pb\n  ```\n  \n### 3. Test your model\n  Run cds.py\n  ```\n  root@europa:~# python cds.py --video vid.mp4 --intensity 100 --verbosity 2 --sensitivity 0.8 --graph CDS_output_graph.pb \n  --labels CDS_output_labels.txt\n  ```\n### 4. Results-\n\nIf it works perfectly then you should get something like this\n\n```\nroot@europa:~# python cds.py --video vid.mp4 --intensity 100 --verbosity 2 --sensitivity 0.8 --graph CDS_output_graph.pb \n  --labels CDS_output_labels.txt\nSuccessfully created the directory blacklist/\nWidth:\t\t1280.0\nHeight:\t\t720.0\nFPS:\t\t24.0\nTotal Frames:\t9611.0\nLength:\t\t400.458333333 sec\ncurrent frame 0\ncurrent frame 100\ncurrent frame 200\ncurrent frame 300\ncurrent frame 400\n.\n.\n.\ncurrent frame 9400\ncurrent frame 9500\ncurrent frame 9600\n.....................................................\nhelmets : 1.8386348802086383 %\npistols : 0.7111849018694115 %\nrifles : 0.6209323493484098 %\nwoman : 11.68438792073656 %\nrevolvers : 0.45700693417348953 %\nman : 85.61387554240541 %\n-----------------------------------------------------\nTotal time taken:\t19.4948489666\n```\n\n## 5. Retraining your model- \n You may need to retrain your model to improve its accuracy. You can therefore use the trainer.py to retrain your model with more dataset.\n ```\n root@europa:~# python trainer.py --bottleneck_dir bottlenecks/ --image_dir training_set/ --output_labels CDS_output_labels.txt \n  --output_graph CDS_output_graph.pb --how_many_training_steps 20000\n  ```\n  \n \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feuropa502%2Fcds","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feuropa502%2Fcds","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feuropa502%2Fcds/lists"}