{"id":34702028,"url":"https://github.com/hubmapconsortium/pas-ftu-segmentation-pipeline","last_synced_at":"2026-05-25T06:33:14.681Z","repository":{"id":47481965,"uuid":"516043503","full_name":"hubmapconsortium/pas-ftu-segmentation-pipeline","owner":"hubmapconsortium","description":null,"archived":false,"fork":false,"pushed_at":"2026-03-02T14:57:40.000Z","size":391,"stargazers_count":0,"open_issues_count":3,"forks_count":0,"subscribers_count":6,"default_branch":"main","last_synced_at":"2026-03-02T17:59:40.911Z","etag":null,"topics":["ot2od030545"],"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/hubmapconsortium.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,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2022-07-20T15:49:09.000Z","updated_at":"2026-03-02T14:25:37.000Z","dependencies_parsed_at":"2024-12-10T00:32:32.328Z","dependency_job_id":null,"html_url":"https://github.com/hubmapconsortium/pas-ftu-segmentation-pipeline","commit_stats":null,"previous_names":[],"tags_count":7,"template":false,"template_full_name":null,"purl":"pkg:github/hubmapconsortium/pas-ftu-segmentation-pipeline","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hubmapconsortium%2Fpas-ftu-segmentation-pipeline","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hubmapconsortium%2Fpas-ftu-segmentation-pipeline/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hubmapconsortium%2Fpas-ftu-segmentation-pipeline/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hubmapconsortium%2Fpas-ftu-segmentation-pipeline/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hubmapconsortium","download_url":"https://codeload.github.com/hubmapconsortium/pas-ftu-segmentation-pipeline/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hubmapconsortium%2Fpas-ftu-segmentation-pipeline/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33462841,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-25T06:15:14.662Z","status":"ssl_error","status_checked_at":"2026-05-25T06:14:31.284Z","response_time":57,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["ot2od030545"],"created_at":"2025-12-24T22:53:33.326Z","updated_at":"2026-05-25T06:33:14.656Z","avatar_url":"https://github.com/hubmapconsortium.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 1-Tom\n\n### Description\n- The model uses a single U-Net SeResNext101 architecture with Convolutional Block Attention Module (CBAM), hypercolumns, and deep supervision. \n- It reads the WSIs as tiled 1024x1024 pixel images and then further resized as 320x320 tiles and sampled using a balanced sampling strategy. \n- The model is trained using a combination of Binary Cross-entropy loss and Lovász Hinge loss, and the optimizer used is SGD (Stochastic gradient descent). Training is for 20 epochs, with a learning rate of 1e-4 to 1e-6 and batch size of 8.\n- For the model trained on colon data from scratch or using transfer learning, the training is done for 50-100 epochs and the validation set is increased from 1 slide to 2 slides.\n\n### Requirements\n- albumentations\n- opencv-python\n- pandas\n- torch\n- tqdm\n- Python 3\n- CUDA \n- cuddn \n- nvidia drivers \n- See `kaggle-hubmap-main/requirements.txt` file for a detailed list of dependencies.\n\n### Usage\n- Use Inference.py to run inference on a dataset.\n- Use train folder to train on a dataset.\n    cd src\n    cd 01_data_preparation/01_01\n    python data_preparation_01_01.py\n    cd ..\n    cd 01_02\n    python data_preparation_01_01.py\n    cd ..\n    cd ..\n    cd 02_train\n    python train_02.py\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhubmapconsortium%2Fpas-ftu-segmentation-pipeline","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhubmapconsortium%2Fpas-ftu-segmentation-pipeline","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhubmapconsortium%2Fpas-ftu-segmentation-pipeline/lists"}