{"id":13482924,"url":"https://github.com/zsdonghao/Spatial-Transformer-Nets","last_synced_at":"2025-03-27T13:33:07.960Z","repository":{"id":72877677,"uuid":"95227794","full_name":"zsdonghao/Spatial-Transformer-Nets","owner":"zsdonghao","description":"Spatial Transformer Nets in TensorFlow/ TensorLayer","archived":false,"fork":false,"pushed_at":"2019-06-17T06:50:54.000Z","size":237,"stargazers_count":36,"open_issues_count":3,"forks_count":6,"subscribers_count":6,"default_branch":"master","last_synced_at":"2024-10-29T20:00:01.342Z","etag":null,"topics":["cnn","deep-learning","spatial-transformer-network","tensorflow","tensorflow-tutorials","tensorlayer"],"latest_commit_sha":null,"homepage":"https://github.com/zsdonghao/tensorlayer","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/zsdonghao.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":"2017-06-23T14:28:55.000Z","updated_at":"2024-10-15T10:22:36.000Z","dependencies_parsed_at":"2024-01-07T10:56:32.187Z","dependency_job_id":null,"html_url":"https://github.com/zsdonghao/Spatial-Transformer-Nets","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zsdonghao%2FSpatial-Transformer-Nets","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zsdonghao%2FSpatial-Transformer-Nets/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zsdonghao%2FSpatial-Transformer-Nets/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zsdonghao%2FSpatial-Transformer-Nets/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zsdonghao","download_url":"https://codeload.github.com/zsdonghao/Spatial-Transformer-Nets/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222262592,"owners_count":16957612,"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":["cnn","deep-learning","spatial-transformer-network","tensorflow","tensorflow-tutorials","tensorlayer"],"created_at":"2024-07-31T17:01:06.747Z","updated_at":"2024-10-30T16:31:53.122Z","avatar_url":"https://github.com/zsdonghao.png","language":"Python","funding_links":[],"categories":["Models/Projects","2. General Computer Vision"],"sub_categories":["1.2 DatasetAPI and TFRecord Examples"],"readme":"# [MOVED TO HERE](https://github.com/tensorlayer/tensorlayer/tree/master/examples/spatial_transformer_network)\n\n# Spatial Transformer Networks\n\n[Spatial Transformer Networks](https://arxiv.org/abs/1506.02025)  (STN) is a dynamic mechanism that produces transformations of input images (or feature maps)including  scaling, cropping, rotations, as well as non-rigid deformations. This enables the network to not only select regions of an image that are most relevant (attention), but also to transform those regions to simplify recognition in the following layers. \n\nVideo for different transformation [click me](https://drive.google.com/file/d/0B1nQa_sA3W2iN3RQLXVFRkNXN0k/view).\n\nIn this repositary, we implemented a STN for [2D Affine Transformation](https://en.wikipedia.org/wiki/Affine_transformation) on MNIST dataset. We generated images with size of 40x40 from the original MNIST dataset, and distorted the images by random rotation, shifting, shearing and zoom in/out. The STN was able to learn to automatically apply transformations on distorted images via classification task.\n\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://github.com/zsdonghao/Spatial-Transformer-Nets/blob/master/images/transform.jpeg\" width=\"50%\" height=\"50%\"/\u003e\n    \u003cbr\u003e  \n    \u003cem align=\"center\"\u003eFig 1：Transformation\u003c/em\u003e  \n\u003c/div\u003e\n\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://github.com/zsdonghao/Spatial-Transformer-Nets/blob/master/images/network.jpeg\" width=\"50%\" height=\"50%\"/\u003e\n    \u003cbr\u003e  \n    \u003cem align=\"center\"\u003eFig 2：Network\u003c/em\u003e  \n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://github.com/zsdonghao/Spatial-Transformer-Nets/blob/master/images/formula.jpeg\" width=\"50%\" height=\"50%\"/\u003e\n    \u003cbr\u003e  \n    \u003cem align=\"center\"\u003eFig 3：Formula\u003c/em\u003e  \n\u003c/div\u003e\n\n## Result\n\nAfter classification task, the STN is able to transform the distorted image from Fig 4 back to Fig 5.\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://github.com/zsdonghao/Spatial-Transformer-Nets/blob/master/images/before_stn.png\" width=\"50%\" height=\"50%\"/\u003e\n    \u003cbr\u003e  \n    \u003cem align=\"center\"\u003eFig 4: Input\u003c/em\u003e  \n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://github.com/zsdonghao/Spatial-Transformer-Nets/blob/master/images/after_stn.png\" width=\"50%\" height=\"50%\"/\u003e\n    \u003cbr\u003e  \n    \u003cem align=\"center\"\u003eFig 5: Output\u003c/em\u003e  \n\u003c/div\u003e\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzsdonghao%2FSpatial-Transformer-Nets","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzsdonghao%2FSpatial-Transformer-Nets","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzsdonghao%2FSpatial-Transformer-Nets/lists"}