{"id":20580916,"url":"https://github.com/nikhilroxtomar/multiclass-image-segmentation-using-unetr-in-tensorflow","last_synced_at":"2025-07-31T17:40:11.380Z","repository":{"id":220512267,"uuid":"751835183","full_name":"nikhilroxtomar/Multiclass-Image-Segmentation-using-UNETR-in-TensorFlow","owner":"nikhilroxtomar","description":"Multiclass Image Segmentation on Human Face Segmentation in TensorFlow","archived":false,"fork":false,"pushed_at":"2024-02-02T12:49:07.000Z","size":2623,"stargazers_count":4,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-11-16T06:28:02.746Z","etag":null,"topics":["multiclass-segmentation","tensorflow","unet","unet-transformer","unetr","unetr-segmentation"],"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/nikhilroxtomar.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}},"created_at":"2024-02-02T12:37:40.000Z","updated_at":"2024-02-18T19:30:42.000Z","dependencies_parsed_at":"2024-02-02T14:17:09.738Z","dependency_job_id":"8f35b197-59f1-4d41-b8d9-c43f65dab812","html_url":"https://github.com/nikhilroxtomar/Multiclass-Image-Segmentation-using-UNETR-in-TensorFlow","commit_stats":null,"previous_names":["nikhilroxtomar/multiclass-image-segmentation-using-unetr-in-tensorflow"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nikhilroxtomar%2FMulticlass-Image-Segmentation-using-UNETR-in-TensorFlow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nikhilroxtomar%2FMulticlass-Image-Segmentation-using-UNETR-in-TensorFlow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nikhilroxtomar%2FMulticlass-Image-Segmentation-using-UNETR-in-TensorFlow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nikhilroxtomar%2FMulticlass-Image-Segmentation-using-UNETR-in-TensorFlow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nikhilroxtomar","download_url":"https://codeload.github.com/nikhilroxtomar/Multiclass-Image-Segmentation-using-UNETR-in-TensorFlow/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":234283415,"owners_count":18808024,"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":["multiclass-segmentation","tensorflow","unet","unet-transformer","unetr","unetr-segmentation"],"created_at":"2024-11-16T06:26:02.277Z","updated_at":"2025-01-16T22:31:57.438Z","avatar_url":"https://github.com/nikhilroxtomar.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Multiclass-Image-Segmentation-using-UNETR-in-TensorFlow\nThis GitHub repository demonstrates the utilization of UNETR for multiclass image segmentation on the Landmark Guided Face Parsing dataset (LaPa) dataset.\n.\n\n## Architecture\n\n| ![The block diagram of the Original UNETR model.](figures/unetr_architecture.png) |\n| :--: |\n| *The block diagram of the Original UNETR model.* |\n\n## Dataset\nLaPa stands for Landmark guided face Parsing dataset (LaPa). It is a large-scale dataset for human face parsing. It consists of more than 22,000 facial images with abundant variations in expression, pose and occlusion, and each image of LaPa is provided with a 11-category pixel-level label map and 106-point landmarks.\n\u003cbr/\u003e \u003cbr/\u003e\nDownload the dataset: [Landmark guided face Parsing dataset (LaPa)](https://drive.google.com/file/d/1XOBoRGSraP50_pS1YPB8_i8Wmw_5L-NG/view?usp=sharing)\n\u003cbr/\u003e \u003cbr/\u003e\nFor more: [LaPa-Dataset for face parsing](https://github.com/jd-opensource/lapa-dataset)\n\n## Results\nThe sequence in the images below is `Input Image`, `Ground Truth` and `Prediction`. \u003cbr/\u003e \u003cbr/\u003e\n| ![](results/115769026_1.png) |\n| :--: |\n| ![](results/101972691_1.png) |\n| ![](results/141022532_0.png) |\n| ![](results/218281108_2.png) |\n| ![](results/1048174932_2.png) |\n\n## How to improve\n- Train on more epochs.\n- Increase the input image resolution.\n- Apply data augmentation.\n\n\n## Contact\nFor more follow me on:\n\n- \u003ca href=\"https://www.youtube.com/idiotdeveloper\"\u003e YouTube \u003c/a\u003e\n- \u003ca href=\"https://facebook.com/idiotdeveloper\"\u003e Facebook \u003c/a\u003e\n- \u003ca href=\"https://twitter.com/nikhilroxtomar\"\u003e Twitter \u003c/a\u003e\n- \u003ca href=\"https://www.instagram.com/nikhilroxtomar\"\u003e Instagram \u003c/a\u003e\n- \u003ca href=\"https://t.me/idiotdeveloper\"\u003e Telegram \u003c/a\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnikhilroxtomar%2Fmulticlass-image-segmentation-using-unetr-in-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnikhilroxtomar%2Fmulticlass-image-segmentation-using-unetr-in-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnikhilroxtomar%2Fmulticlass-image-segmentation-using-unetr-in-tensorflow/lists"}