{"id":13499121,"url":"https://github.com/Randl/ShuffleNetV2-pytorch","last_synced_at":"2025-03-29T04:30:31.120Z","repository":{"id":34728337,"uuid":"143295986","full_name":"Randl/ShuffleNetV2-pytorch","owner":"Randl","description":"Implementation of ShuffleNetV2 for pytorch","archived":false,"fork":false,"pushed_at":"2022-04-17T04:44:41.000Z","size":10736,"stargazers_count":189,"open_issues_count":5,"forks_count":52,"subscribers_count":9,"default_branch":"master","last_synced_at":"2024-08-01T22:50:09.301Z","etag":null,"topics":["cnn-model","pytorch","shufflenetv2"],"latest_commit_sha":null,"homepage":null,"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/Randl.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":"2018-08-02T13:06:48.000Z","updated_at":"2024-04-16T13:55:23.000Z","dependencies_parsed_at":"2022-08-08T01:16:34.308Z","dependency_job_id":null,"html_url":"https://github.com/Randl/ShuffleNetV2-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/Randl%2FShuffleNetV2-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Randl%2FShuffleNetV2-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Randl%2FShuffleNetV2-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Randl%2FShuffleNetV2-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Randl","download_url":"https://codeload.github.com/Randl/ShuffleNetV2-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222455962,"owners_count":16987579,"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-model","pytorch","shufflenetv2"],"created_at":"2024-07-31T22:00:29.331Z","updated_at":"2024-10-31T17:31:32.712Z","avatar_url":"https://github.com/Randl.png","language":"Python","funding_links":[],"categories":["Papers\u0026Codes","DLA"],"sub_categories":["ShuffleNetV2"],"readme":"# ShuffleNetv2 in PyTorch\n\nAn implementation of `ShuffleNetv2` in PyTorch. `ShuffleNetv2` is an efficient convolutional neural network architecture for mobile devices. For more information check the paper:\n[ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://arxiv.org/abs/1807.11164)\n\n## Usage\n\nClone the repo:\n```bash\ngit clone https://github.com/Randl/ShuffleNetV2-pytorch\npip install -r requirements.txt\n```\n\nUse the model defined in `model.py` to run ImageNet example:\n```bash\npython imagenet.py --dataroot \"/path/to/imagenet/\"\n```\n\nTo continue training from checkpoint\n```bash\npython imagenet.py --dataroot \"/path/to/imagenet/\" --resume \"/path/to/checkpoint/folder\"\n```\n## Results\n\n\nFor x0.5 model I achieved 0.4% lower top-1 accuracy than claimed.\n\n|Classification Checkpoint| MACs (M)   | Parameters (M)| Top-1 Accuracy| Top-5 Accuracy|  Claimed top-1|  Claimed top-5|\n|-------------------------|------------|---------------|---------------|---------------|---------------|---------------|\n|      [shufflenet_v2_0.5]|41          |1.37           |          59.86|          81.63|           60.3|              -|\n\nYou can test it with\n```bash\npython imagenet.py --dataroot \"/path/to/imagenet/\" --resume \"results/shufflenet_v2_0.5/model_best.pth.tar\" -e --scaling 0.5\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRandl%2FShuffleNetV2-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FRandl%2FShuffleNetV2-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRandl%2FShuffleNetV2-pytorch/lists"}