{"id":24989815,"url":"https://github.com/clementsan/ir-tp-net","last_synced_at":"2026-05-03T04:36:36.147Z","repository":{"id":213402014,"uuid":"734046857","full_name":"clementsan/ir-tp-net","owner":"clementsan","description":"AI-based 3D depth sensing from stereo vision systems","archived":false,"fork":false,"pushed_at":"2023-12-28T18:15:34.000Z","size":162,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-04T13:03:32.410Z","etag":null,"topics":["deep-learning","depth-sensing","pytorch","stereo-vision","torchio"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/clementsan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2023-12-20T18:26:15.000Z","updated_at":"2023-12-21T00:18:00.000Z","dependencies_parsed_at":"2023-12-27T21:12:32.530Z","dependency_job_id":"8901dcf9-b1cc-4d35-ad6b-177fa5f3116e","html_url":"https://github.com/clementsan/ir-tp-net","commit_stats":null,"previous_names":["clementsan/ir-tp-net"],"tags_count":19,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/clementsan%2Fir-tp-net","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/clementsan%2Fir-tp-net/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/clementsan%2Fir-tp-net/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/clementsan%2Fir-tp-net/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/clementsan","download_url":"https://codeload.github.com/clementsan/ir-tp-net/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246180923,"owners_count":20736460,"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":["deep-learning","depth-sensing","pytorch","stereo-vision","torchio"],"created_at":"2025-02-04T13:03:35.912Z","updated_at":"2026-05-03T04:36:31.103Z","avatar_url":"https://github.com/clementsan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI-based 3D depth sensing from stereo vision systems\n\nMulti-input neural network to predict disparity maps \n\nNetwork name: ir-tp-net (infrared tile processing network)\n\n\n## Notes\n\n### ir-tp-net\n\nir-tp-net is a two-stage deep neural network (DNN). Stage 1 includes dynamic parallel sub-networks, that are then concatenated to form a single sub-network in stage 2.\n\nThis python library works on specific multi-layer TIFF images, that were generated via a complex preprocessing \nstage for multi-sensor stereo-vision (including image correction and 2D phase correlation).\n\n### Related github repo\n\nThe additional github repository [\"disp-map-analysis\"](https://github.com/clementsan/disp-map-analysis) provides additional pre-processing and post-processing python scripts.\n\n\n## Installation and requirements \n\nInstallation using conda\n```\n\u003e conda create --name \u003cenv_name\u003e --file \u003cconda_environment.yaml\u003e\n\u003e conda activate \u003cenv_name\u003e\n```\nOR \n```\n\u003e source activate \u003cenv_name\u003e\n```\n\nGeneral libraries being used:\n -\tpython 3.9 \n -\tpillow, numpy, pandas, matplotlib \n -\tpytorch, torchio, imageio, tensorboard\n -\tscikit-learn, yaml\n\n\n## Execution\n\n### DNN training using configuration file\n\nCommand line:\n```\n\u003e python3 AI_Training.py --config AI_Training_Config.yaml\n```\n \n### DNN inference using configuration file\n\nCommand line:\n```\n\u003e python3 AI_Inference_CSV.py --config AI_Inference_Config.yaml --verbose\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fclementsan%2Fir-tp-net","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fclementsan%2Fir-tp-net","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fclementsan%2Fir-tp-net/lists"}