{"id":20663706,"url":"https://github.com/vita-group/lth-pass","last_synced_at":"2025-04-19T15:56:11.063Z","repository":{"id":107046504,"uuid":"435386745","full_name":"VITA-Group/LTH-Pass","owner":"VITA-Group","description":"[TMLR] \"Can You Win Everything with Lottery Ticket?\"  by Tianlong Chen, Zhenyu Zhang, Jun Wu, Randy Huang, Sijia Liu, Shiyu Chang, Zhangyang Wang","archived":false,"fork":false,"pushed_at":"2022-09-08T00:37:07.000Z","size":8950,"stargazers_count":10,"open_issues_count":0,"forks_count":2,"subscribers_count":7,"default_branch":"main","last_synced_at":"2025-03-29T09:42:05.660Z","etag":null,"topics":["adversarial-robustness","explanability","flatness","generalization","interpretability","loss-landscape","lottery-ticket-hypothesis","out-of-distribution-detection","pac-bayes","robustness","uncertainty","winning-tickets"],"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/VITA-Group.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,"governance":null,"roadmap":null,"authors":null}},"created_at":"2021-12-06T06:36:41.000Z","updated_at":"2024-02-26T21:55:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"f9331a97-212b-4a40-b3ea-c4cc0701e929","html_url":"https://github.com/VITA-Group/LTH-Pass","commit_stats":{"total_commits":8,"total_committers":2,"mean_commits":4.0,"dds":0.5,"last_synced_commit":"0f740edff443b286325e056639dbf6a7606c7745"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VITA-Group%2FLTH-Pass","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VITA-Group%2FLTH-Pass/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VITA-Group%2FLTH-Pass/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VITA-Group%2FLTH-Pass/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/VITA-Group","download_url":"https://codeload.github.com/VITA-Group/LTH-Pass/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249731258,"owners_count":21317342,"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":["adversarial-robustness","explanability","flatness","generalization","interpretability","loss-landscape","lottery-ticket-hypothesis","out-of-distribution-detection","pac-bayes","robustness","uncertainty","winning-tickets"],"created_at":"2024-11-16T19:19:28.145Z","updated_at":"2025-04-19T15:56:11.039Z","avatar_url":"https://github.com/VITA-Group.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Can You Win Everything with Lottery Ticket?\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)\n\nCode for this **preprint** paper [Can You Win Everything with Lottery Ticket?]()\n\nTianlong Chen, Zhenyu Zhang, Jun Wu, Randy Huang, Sijia Liu, Shiyu Chang, Zhangyang Wang\n\n## Overview\n\n\n\n## Experiment Results\n\n![](./Figs/Res.png)\n\n\n\n## Prerequisites\n\n- pytorch\n\n- torchvision\n\n- advertorch\n\n\n\n## Usages\n\nEvaluation on CIFAR-10/100 \n\n```\npython -u main_eval.py \\\n\t--data [data-direction] \\\n\t--dataset cifar10 \\ # choose from [cifar10, cifar100]\n\t--arch resnet20s \\ # choose from [resnet20s,resnet18,wideresnet]\n\t--pretrained [pretrained-weight] \\ \n\t--eval_mode accuracy,robustness,corruption,ood,calibration,interpretation,pac_bayes_weight,pac_bayes_input \\\n\t--output_file result.pt \\\n\t--test_randinit_off \\\n\t--image_number 1000 \n```\n\nEvaluation on ImageNet \n\n```\npython -u main_eval_imagenet.py \\\n    --data [data-direction] \\\n    --arch resnet50 \\\n    --pretrained [pretrained-weight] \\\n    --eval_mode accuracy,robustness,corruption,ood,calibration,interpretation,pac_bayes_weight,pac_bayes_input \\\n    --output_file result.pt \n```\n\nEvaluation for Hessian\n\n```\npython -u vis_pyhessian_analysis.py \\\n    --data [data-direction] \\\n    --dataset [dataset] \\ choose from [cifar10, cifar100, imagenet]\n    --arch [network-architecture] \\ choose from [resnet20s,resnet18,wideresnet,resnet50]\n    --pretrained [pretrained-weight] \\\n    --output_file result.pt \\\n    --mode weight,input\n```\n\nComposition neurons\n\n`cd composition-neuron`, which is modified from https://github.com/jayelm/compexp\n\n## Citation\n\n```\nTBD\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvita-group%2Flth-pass","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvita-group%2Flth-pass","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvita-group%2Flth-pass/lists"}