{"id":13499016,"url":"https://github.com/ry/tensorflow-resnet","last_synced_at":"2025-03-29T03:32:14.809Z","repository":{"id":38361601,"uuid":"48251594","full_name":"ry/tensorflow-resnet","owner":"ry","description":"ResNet model in TensorFlow","archived":true,"fork":false,"pushed_at":"2018-06-16T02:54:27.000Z","size":1423,"stargazers_count":1657,"open_issues_count":38,"forks_count":625,"subscribers_count":57,"default_branch":"master","last_synced_at":"2024-10-31T17:39:06.610Z","etag":null,"topics":[],"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/ry.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":"2015-12-18T19:03:22.000Z","updated_at":"2024-10-14T06:20:23.000Z","dependencies_parsed_at":"2022-07-12T17:27:45.786Z","dependency_job_id":null,"html_url":"https://github.com/ry/tensorflow-resnet","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/ry%2Ftensorflow-resnet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ry%2Ftensorflow-resnet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ry%2Ftensorflow-resnet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ry%2Ftensorflow-resnet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ry","download_url":"https://codeload.github.com/ry/tensorflow-resnet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246135747,"owners_count":20729056,"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":[],"created_at":"2024-07-31T22:00:26.080Z","updated_at":"2025-03-29T03:32:14.480Z","avatar_url":"https://github.com/ry.png","language":"Python","funding_links":[],"categories":["Papers\u0026Codes","Python","Table of Contents","Deep Residual Learning"],"sub_categories":["ResNet","Implementations"],"readme":"This code is *very old* and doesn't run on modern TensorFlow. Indeed, TF now\nincludes a resnet model in its core library:\nhttps://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/slim/python/slim/nets/resnet_v1.py\n\nAlso checkout my new ML project at http://propelml.org/\n\n\n\n# ResNet in TensorFlow\n\nImplemenation of [Deep Residual Learning for Image\nRecognition](http://arxiv.org/abs/1512.03385).  Includes a tool to use He et\nal's published trained Caffe weights in TensorFlow.\n\nMIT license. Contributions welcome.\n\n## Goals\n\n* Be able to use the pre-trained model's that [Kaiming He has provided for\n  Caffe](https://github.com/KaimingHe/deep-residual-networks). The `convert.py`\n  will convert the weights for use with TensorFlow.\n\n* Implemented in the style of\n  [Inception](https://github.com/tensorflow/models/tree/master/inception/inception)\n  not using any classes and making heavy use of variable scope. It should be\n  easily usable in other models.\n\n* Foundation to experiment with changes to ResNet like [stochastic\n  depth](https://arxiv.org/abs/1603.09382), [shared weights at each\n  scale](https://arxiv.org/abs/1604.03640), and 1D convolutions for audio. (Not yet implemented.)\n\n* ResNet is fully convolutional and the implementation should allow inputs to be any size.\n\n* Be able to train out of the box on CIFAR-10, 100, and ImageNet. (Implementation incomplete)\n\n\n## Pretrained Model\n\nTo convert the published Caffe pretrained model, run `convert.py`. However\nCaffe is annoying to install so I'm providing a download of the output of\nconvert.py: \n\n[tensorflow-resnet-pretrained-20160509.tar.gz.torrent](https://raw.githubusercontent.com/ry/tensorflow-resnet/master/data/tensorflow-resnet-pretrained-20160509.tar.gz.torrent)  464M\n\n\n## Notes\n\n* This code depends on [TensorFlow git commit\n  cf7ce8](https://github.com/tensorflow/tensorflow/commit/cf7ce8a7879b6a7ba90441724ea3f8353917a515)\n  or later because ResNet needs 1x1 convolutions with stride 2. TF 0.8 is not new\n  enough.\n\n* The `convert.py` script checks that activations are similiar to the caffe version\n  but it's not exactly the same. This is probably due to differences between how\n  TF and Caffe handle padding. Also preprocessing is done with color-channel means \n  instead of pixel-wise means.\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fry%2Ftensorflow-resnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fry%2Ftensorflow-resnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fry%2Ftensorflow-resnet/lists"}