{"id":15649769,"url":"https://github.com/erogol/seg-torch","last_synced_at":"2025-04-30T16:29:39.701Z","repository":{"id":145077767,"uuid":"77091979","full_name":"erogol/seg-torch","owner":"erogol","description":"Segmentation with deep learning","archived":false,"fork":false,"pushed_at":"2016-12-29T20:22:17.000Z","size":53667,"stargazers_count":37,"open_issues_count":0,"forks_count":10,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-03-30T17:51:12.792Z","etag":null,"topics":["deep-learning","image-segmentation","lua","seg-torch","segmentation","torch"],"latest_commit_sha":null,"homepage":null,"language":"Lua","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/erogol.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2016-12-21T22:53:11.000Z","updated_at":"2024-01-04T16:09:58.000Z","dependencies_parsed_at":null,"dependency_job_id":"75d1ad87-4d79-4c1f-b780-d1cd1b5b0069","html_url":"https://github.com/erogol/seg-torch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erogol%2Fseg-torch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erogol%2Fseg-torch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erogol%2Fseg-torch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erogol%2Fseg-torch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/erogol","download_url":"https://codeload.github.com/erogol/seg-torch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251742082,"owners_count":21636378,"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","image-segmentation","lua","seg-torch","segmentation","torch"],"created_at":"2024-10-03T12:31:56.387Z","updated_at":"2025-04-30T16:29:39.572Z","avatar_url":"https://github.com/erogol.png","language":"Lua","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Seg-Torch for Image Segmentation with Torch\n\nThis work was sparked by my personal research on simple segmentation methods based on deep learning. It is the harvest of two great predecessors;\n\n* https://github.com/e-lab/ENet-training\n* https://github.com/fedor-chervinskii/segnet-torch\n  * (real project page) http://mi.eng.cam.ac.uk/projects/segnet/\n\nHowever this code includes radical differences (such as data loading, augmentation, memory optimization) and it has more generic type of implementation suitable for use in any custom project. You only need to modify data-loader files data/custom-gen.lua and data/custom.lua.\n\nBe warned this is susceptible to bugs. Any pull request is appreciated.\n\nCheck train_scripts/ for example execution.\n\n# Models\n\n* SegNet: Very simple encoder-decoder network, segmenting end2end\n* EroNet: Very similar but it chops Batch-Normalization and uses ELU activation. It is lower in accuracy but faster in training.\n\n# Example Results\n\nexp_model/ includes a proof of concept on CamVid dataset. If you compare the results with the real-project this implementation has higher values interestingly (at least for me) :) .\n\nModel will be shared on Dropbox, as soon as I find some time to do so.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ferogol%2Fseg-torch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ferogol%2Fseg-torch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ferogol%2Fseg-torch/lists"}