{"id":13422211,"url":"https://github.com/eambutu/snail-pytorch","last_synced_at":"2025-03-15T11:31:24.597Z","repository":{"id":68842943,"uuid":"134166699","full_name":"eambutu/snail-pytorch","owner":"eambutu","description":"Implementation of \"A Simple Neural Attentive Meta-Learner\" (SNAIL, https://arxiv.org/pdf/1707.03141.pdf) in PyTorch","archived":false,"fork":false,"pushed_at":"2019-07-06T00:29:24.000Z","size":17,"stargazers_count":145,"open_issues_count":3,"forks_count":28,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-07-31T23:44:52.586Z","etag":null,"topics":["cnn","python","pytorch","snail"],"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/eambutu.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":"2018-05-20T16:19:23.000Z","updated_at":"2024-07-27T10:46:26.000Z","dependencies_parsed_at":null,"dependency_job_id":"6f2ec0ac-e618-4c5f-b0ab-87646975098d","html_url":"https://github.com/eambutu/snail-pytorch","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/eambutu%2Fsnail-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eambutu%2Fsnail-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eambutu%2Fsnail-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eambutu%2Fsnail-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/eambutu","download_url":"https://codeload.github.com/eambutu/snail-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221572068,"owners_count":16845574,"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","python","pytorch","snail"],"created_at":"2024-07-30T23:00:39.293Z","updated_at":"2024-10-26T19:32:34.127Z","avatar_url":"https://github.com/eambutu.png","language":"Python","funding_links":[],"categories":["A Simple Neural Attentive Meta-Learner. ICLR 2018"],"sub_categories":[],"readme":"# A Simple Neural Attentive Meta-Learner (SNAIL) in PyTorch\nAn implementation of Simple Neural Attentive Meta-Learner (SNAIL) ([paper](https://arxiv.org/pdf/1707.03141.pdf)) in PyTorch.\n\nMuch of the boiler plate code for setting up datasets and what not came from a PyTorch implementation of [Prototypical Networks](https://github.com/orobix/Prototypical-Networks-for-Few-shot-Learning-PyTorch/blob/master/README.md).\n\n## Mini-Imagenet Dataset\n\nFollow the instructions here: https://github.com/renmengye/few-shot-ssl-public\nto download the mini-imagenet dataset.\n\n## Performance\n\nBelow are the following attempts to reproduce the results in the reference\npaper:\n\n### Omniglot:\n\n| Model | 1-shot (5-way Acc.) | 5-shot (5-way Acc.) | 1 -shot (20-way Acc.) | 5-shot (20-way Acc.)|\n| --- | --- | --- | --- | --- |\n| Reference Paper | 99.07% | 99.78% | 97.64% | 99.36%|\n| This repo | 98.31%\\* | 99.26%\\*\\* | 93.75%° | 97.88%°° |\n\n\\* achieved running `python train.py --exp omniglot_5way_1shot --cuda`\n\n\\* achieved running `python train.py --exp omniglot_5way_5shot --num_samples 5 --cuda`\n\n\\* achieved running `python train.py --exp omniglot_20way_1shot --num_cls 20 --cuda`\n\n\\* achieved running `python train.py --exp omniglot_20way_5shot --num_cls 20\n--num_samples 5 --cuda`\n\n### Mini-Imagenet:\n\nIn progress. Writing the code for the experiments should be done soon but the\nmain bottleneck in these experiments for me is compute, if someone would be\nwilling to run and report numbers that would be much appreciated.\n\n### RL:\n\nIn progress.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feambutu%2Fsnail-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feambutu%2Fsnail-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feambutu%2Fsnail-pytorch/lists"}