{"id":50913942,"url":"https://github.com/shivam-21-11/basnet-model_package","last_synced_at":"2026-06-16T13:00:54.251Z","repository":{"id":58492776,"uuid":"532153990","full_name":"Shivam-21-11/Basnet-Model_Package","owner":"Shivam-21-11","description":"BASNet: Boundary-Aware Salient Object Detection","archived":false,"fork":false,"pushed_at":"2022-09-03T06:33:49.000Z","size":28,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-21T08:57:03.970Z","etag":null,"topics":["computer-vision","image-segmentation","obejct-detection","tensorflow"],"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/Shivam-21-11.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}},"created_at":"2022-09-03T04:25:35.000Z","updated_at":"2022-09-03T06:09:01.000Z","dependencies_parsed_at":"2022-09-03T13:00:48.307Z","dependency_job_id":null,"html_url":"https://github.com/Shivam-21-11/Basnet-Model_Package","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Shivam-21-11/Basnet-Model_Package","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shivam-21-11%2FBasnet-Model_Package","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shivam-21-11%2FBasnet-Model_Package/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shivam-21-11%2FBasnet-Model_Package/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shivam-21-11%2FBasnet-Model_Package/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Shivam-21-11","download_url":"https://codeload.github.com/Shivam-21-11/Basnet-Model_Package/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shivam-21-11%2FBasnet-Model_Package/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34406824,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-16T02:00:06.860Z","response_time":126,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["computer-vision","image-segmentation","obejct-detection","tensorflow"],"created_at":"2026-06-16T13:00:28.937Z","updated_at":"2026-06-16T13:00:54.246Z","avatar_url":"https://github.com/Shivam-21-11.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SOD-BASNET-Py\r\n*This is Official repository for the  SODBASNET python module* \r\n# BASNet: Boundary-Aware Salient Object Detection\r\n\r\n- Deep Convolutional Neural Networks have been adopted for salient object detection and achieved the state-of-the-art performance. Most of the previous works however focus on region accuracy but not on the boundary quality.\r\n- In this project, we propose a predict-refine architecture, BASNet, and a new hybrid loss for Boundary-Aware Salient object detection. Specifically, the architecture is composed of a densely supervised Encoder-Decoder network and a residual refinement module, which are respectively in charge of saliency prediction and saliency map refinement.\r\n- The Research paper referred  is [BASNet: Boundary-Aware Salient Object Detection](https://openaccess.thecvf.com/content_CVPR_2019/papers/Qin_BASNet_Boundary-Aware_Salient_Object_Detection_CVPR_2019_paper.pdf \"BASNet: Boundary-Aware Salient Object Detection\") \r\n\r\n## Objective \r\n- The Official Code for the Basnet Model is provided by the authors on the [github](https://github.com/xuebinqin/BASNet \"github\").\r\n- The Official Deep Learning model is made using Pytorch , my Goal is to create a similar model using tensorflow.\r\n- Why ? Whilst Pytorch provide better developer experience and error handeling, I find Tensorflow to be a great ML Framework to work with for Beginners .  \r\n- So the objective for this repo is to create Basnet Model using Tensorflow.\r\n\r\n## Architecture\r\n- The Architecture Proposed by the authors is predict-refine architecture.\r\n- The Author have used  Transfer Learning  to improve model performance . They Used First 4 layers of the resnet34 model which is pretrained in imagenet dataset.\r\n- But for the sake of understanding abstract architecture of the Basnet model I haven't used the transfer learning method , instead created each layer individually.\r\n\r\n## Loss\r\n- The hybrid loss guides the network to learn the transformation between the input image and the ground truth in a three-level hierarchy – pixel-, patch- and map- level – by fusing Binary Cross Entropy (BCE), Structural SIMilarity (SSIM) and Intersectionover- Union (IoU) losses.\r\n\r\n# Usage Example\r\nPip installing SODBASNET\r\n\r\n`pip install SODBASNET`\r\n\r\nImporting Basnet Model\r\n\r\n```python\r\nfrom BASNET import BasNet\r\nfrom BASNET import iou_loss,ssim_loss,binary_crossentropy\r\n\r\nmodel = BasNet()\r\nmodel.compile(optimizer='adam',\r\nloss=[iou_loss,ssim_loss,binary_crossentropy],\r\nmetrics = ['accuracy'])\r\n\r\n```\r\n\r\n## Thank You \r\n- This is my attempt to build the Basnet model using the research paper . If you find any error or mistakes let me know . Love all the feedbacks.\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshivam-21-11%2Fbasnet-model_package","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshivam-21-11%2Fbasnet-model_package","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshivam-21-11%2Fbasnet-model_package/lists"}