{"id":13499112,"url":"https://github.com/Randl/MobileNetV2-pytorch","last_synced_at":"2025-03-29T04:30:44.300Z","repository":{"id":87383797,"uuid":"117980814","full_name":"Randl/MobileNetV2-pytorch","owner":"Randl","description":"Impementation of MobileNetV2 in pytorch ","archived":false,"fork":false,"pushed_at":"2018-08-28T13:44:34.000Z","size":55557,"stargazers_count":267,"open_issues_count":5,"forks_count":83,"subscribers_count":14,"default_branch":"master","last_synced_at":"2024-08-01T22:50:06.718Z","etag":null,"topics":["cnn","image-classification","mobilenet2","pytorch"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1801.04381","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,"governance":null,"roadmap":null,"authors":null}},"created_at":"2018-01-18T12:37:16.000Z","updated_at":"2024-08-01T10:05:03.000Z","dependencies_parsed_at":null,"dependency_job_id":"b8fd2127-aa3f-4112-8ebb-8a4af6156443","html_url":"https://github.com/Randl/MobileNetV2-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%2FMobileNetV2-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Randl%2FMobileNetV2-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Randl%2FMobileNetV2-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Randl%2FMobileNetV2-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Randl","download_url":"https://codeload.github.com/Randl/MobileNetV2-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222455971,"owners_count":16987581,"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","image-classification","mobilenet2","pytorch"],"created_at":"2024-07-31T22:00:29.046Z","updated_at":"2025-03-29T04:30:44.294Z","avatar_url":"https://github.com/Randl.png","language":"Python","readme":"# MobileNetv2 in PyTorch\n\nAn implementation of `MobileNetv2` in PyTorch. `MobileNetv2` is an efficient convolutional neural network architecture for mobile devices. For more information check the paper:\n[Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation](https://arxiv.org/abs/1801.04381) \n\n## Usage\n\nClone the repo:\n```bash\ngit clone https://github.com/Randl/MobileNetV2-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 run continue training from checkpoint\n```bash\npython imagenet.py --dataroot \"/path/to/imagenet/\" --resume \"/path/to/checkpoint/folder\"\n```\n## Results\n\nFor x1.0 model I achieved 0.3% higher 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|   [mobilenet_v2_1.0_224]|300         |3.47           |          72.10|          90.48|           71.8|           91.0|\n|   [mobilenet_v2_0.5_160]|50          |1.95           |          60.61|          82.87|           61.0|           83.2|\n\nYou can test it with\n```bash\npython imagenet.py --dataroot \"/path/to/imagenet/\" --resume \"results/mobilenet_v2_1.0_224/model_best.pth.tar\" -e\npython imagenet.py --dataroot \"/path/to/imagenet/\" --resume \"results/mobilenet_v2_0.5_160/model_best.pth.tar\" -e --scaling 0.5 --input-size 160\n```\n","funding_links":[],"categories":["Papers\u0026Codes","DLA"],"sub_categories":["MobileNetV2"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRandl%2FMobileNetV2-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FRandl%2FMobileNetV2-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRandl%2FMobileNetV2-pytorch/lists"}