{"id":14958911,"url":"https://github.com/uranusx86/binarynet-on-tensorflow","last_synced_at":"2025-05-02T13:30:24.007Z","repository":{"id":42879164,"uuid":"121246885","full_name":"uranusx86/BinaryNet-on-tensorflow","owner":"uranusx86","description":"binary weight neural network implementation on tensorflow","archived":false,"fork":false,"pushed_at":"2018-03-23T13:14:28.000Z","size":11362,"stargazers_count":54,"open_issues_count":0,"forks_count":24,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-07T02:07:56.048Z","etag":null,"topics":["deep-learning","neural-network","python","tensorflow","tensorflow-experiments"],"latest_commit_sha":null,"homepage":null,"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/uranusx86.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}},"created_at":"2018-02-12T12:58:40.000Z","updated_at":"2024-10-18T13:05:35.000Z","dependencies_parsed_at":"2022-07-09T02:00:34.949Z","dependency_job_id":null,"html_url":"https://github.com/uranusx86/BinaryNet-on-tensorflow","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/uranusx86%2FBinaryNet-on-tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uranusx86%2FBinaryNet-on-tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uranusx86%2FBinaryNet-on-tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uranusx86%2FBinaryNet-on-tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/uranusx86","download_url":"https://codeload.github.com/uranusx86/BinaryNet-on-tensorflow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252045989,"owners_count":21685931,"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":["deep-learning","neural-network","python","tensorflow","tensorflow-experiments"],"created_at":"2024-09-24T13:18:29.564Z","updated_at":"2025-05-02T13:30:23.723Z","avatar_url":"https://github.com/uranusx86.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# BinaryNet-on-tensorflow\nbinary weight neural network implementation on tensorflow\n\nThis is an implementation code for reproducing BNN\n\n## How to run\n```\npython mnist.py\npython cifar10.py\n```\n\n## Accuracy\n| DataSet | accuracy |\n|---------|----------|\n| MNIST   |  99.04%  |\n| Cifar10 |  86.18%  |\n\n## Different between paper\nlayer-wise learning rate, paper is layer_lr = 1./sqrt(1.5 / (num_inputs + num_units)), my implement is layer_lr / 4\n\n## Ref\n```\n[BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1\"](http://arxiv.org/abs/1602.02830),\nMatthieu Courbariaux, Yoshua Bengio\n```\nand\n[An implemtation of binaryNet for Keras](https://github.com/DingKe/nn_playground/tree/master/binarynet)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Furanusx86%2Fbinarynet-on-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Furanusx86%2Fbinarynet-on-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Furanusx86%2Fbinarynet-on-tensorflow/lists"}