{"id":13422308,"url":"https://github.com/istarjun/TapNet","last_synced_at":"2025-03-15T11:31:36.289Z","repository":{"id":201746817,"uuid":"186274609","full_name":"istarjun/TapNet","owner":"istarjun","description":"Chainer Implementation of TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning","archived":false,"fork":false,"pushed_at":"2019-10-21T02:47:45.000Z","size":11,"stargazers_count":56,"open_issues_count":4,"forks_count":12,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-10-27T22:33:50.189Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/istarjun.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}},"created_at":"2019-05-12T15:53:52.000Z","updated_at":"2023-12-10T07:57:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"56559fdc-7787-4167-8c7a-ce6d358be2be","html_url":"https://github.com/istarjun/TapNet","commit_stats":null,"previous_names":["istarjun/tapnet"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/istarjun%2FTapNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/istarjun%2FTapNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/istarjun%2FTapNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/istarjun%2FTapNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/istarjun","download_url":"https://codeload.github.com/istarjun/TapNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243724956,"owners_count":20337655,"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":"2024-07-30T23:00:41.405Z","updated_at":"2025-03-15T11:31:36.016Z","avatar_url":"https://github.com/istarjun.png","language":"Python","readme":"# TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning\n\nCode for the ICML 2019 paper TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning\n\n## Dependencies\n* This code is tested on Ubuntu 16.04 with Python 3.6 and chainer 5.20\n\n## Data  \n### miniImageNet\n#Download and unzip \"mini-imagenet.tar.gz\" from Google Drive link [[mini-ImageNet](https://drive.google.com/file/d/1DvYd7LMa0zvlqTM8oBdCWwQSxpZdf_D5/view?usp=sharing)]\n\n#Place ``train.npz``, ``val.npz``, ``test.npz`` files in ``TapNet/miniImageNet_TapNet/data``\n\n\n### tieredImageNet\n#Download and unzip \"tiered-imagenet.tar.gz\" from Google Drive link [[tiered-ImageNet](https://drive.google.com/file/d/1zz7bAYus7EeoMokwUQlLc3OY_eoII8B7/view?usp=sharing)]\n\n#Place images ``.npz`` and labels ``.pkl`` files in ``TapNet/tieredImageNet_TapNet/data``\n\n## Running the code\n\n```\n#For miniImageNet experiment\n\ncd /TapNet/miniImageNet_TapNet/scripts\npython train_TapNet_miniImageNet.py --gpu {GPU device number}\n                                    --n_shot {n_shot}\n                                    --nb_class_train {number of classes in training}\n                                    --nb_class_test {number of classes in test}\n                                    --n_query_train {number of queries per class in training}\n                                    --n_query_test {number of queries per class in test}\n                                    --wd_rate {Weight decay rate}\n                                    \n                                    \n#For tieredImageNet experiment\n\ncd /TapNet/tieredImageNet_TapNet/scripts\npython train_TapNet_tieredImageNet.py --gpu {GPU device number}\n                                    --n_shot {n_shot}\n                                    --nb_class_train {number of classes in training}\n                                    --nb_class_test {number of classes in test}\n                                    --n_query_train {number of queries per class in training}\n                                    --n_query_test {number of queries per class in test}\n                                    --wd_rate {Weight decay rate}\n```\n\n","funding_links":[],"categories":["TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning. ICML 2019"],"sub_categories":["[few-shot 知乎](https://zhuanlan.zhihu.com/p/58298920)"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fistarjun%2FTapNet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fistarjun%2FTapNet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fistarjun%2FTapNet/lists"}