{"id":13499139,"url":"https://github.com/xiaolai-sqlai/mobilenetv3","last_synced_at":"2025-05-15T22:03:09.062Z","repository":{"id":39886242,"uuid":"186247418","full_name":"xiaolai-sqlai/mobilenetv3","owner":"xiaolai-sqlai","description":"mobilenetv3 with pytorch，provide pre-train model","archived":false,"fork":false,"pushed_at":"2023-04-27T03:23:18.000Z","size":125602,"stargazers_count":1707,"open_issues_count":46,"forks_count":344,"subscribers_count":23,"default_branch":"master","last_synced_at":"2025-04-01T05:36:43.977Z","etag":null,"topics":[],"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/xiaolai-sqlai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2019-05-12T11:40:54.000Z","updated_at":"2025-03-31T05:50:42.000Z","dependencies_parsed_at":"2022-07-15T07:31:07.589Z","dependency_job_id":"6c6c8b07-0017-40ef-a7cf-a4db5e29a33b","html_url":"https://github.com/xiaolai-sqlai/mobilenetv3","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/xiaolai-sqlai%2Fmobilenetv3","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiaolai-sqlai%2Fmobilenetv3/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiaolai-sqlai%2Fmobilenetv3/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiaolai-sqlai%2Fmobilenetv3/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xiaolai-sqlai","download_url":"https://codeload.github.com/xiaolai-sqlai/mobilenetv3/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247801175,"owners_count":20998339,"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":"2024-07-31T22:00:29.825Z","updated_at":"2025-04-08T08:15:21.170Z","avatar_url":"https://github.com/xiaolai-sqlai.png","language":"Python","funding_links":[],"categories":["Papers\u0026Codes","DLA","Python"],"sub_categories":["MobileNetV3"],"readme":"# A PyTorch implementation of MobileNetV3\nI retrain the mobilenetv3 with some novel tricks and [timm](https://github.com/huggingface/pytorch-image-models). \nI also provide the train code, pre-training weight and training logs on this project. \n\nYou should use torch.load to load the model.\n```\nfrom mobilenetv3 import MobileNetV3_Small, MobileNetV3_Large\n\n# MobileNetV3_Small\nnet = MobileNetV3_Small()\nnet.load_state_dict(torch.load(\"450_act3_mobilenetv3_small.pth\", map_location='cpu'))\n\n# MobileNetV3_Large\nnet = MobileNetV3_Large()\nnet.load_state_dict(torch.load(\"450_act3_mobilenetv3_large.pth\", map_location='cpu'))\n```\n\nYou could reproduce the model by the code.\n```\nnohup python -u -m torch.distributed.run --nproc_per_node=8 main.py --model mobilenet_v3_small --epochs 300 --batch_size 256 --lr 4e-3 --update_freq 2 --model_ema false --model_ema_eval false --use_amp true --data_path /data/benchmarks/ILSVRC2012 --output_dir ./checkpoint \u0026\n\nnohup python -u -m torch.distributed.run --nproc_per_node=8 main.py --model mobilenet_v3_small --epochs 450 --batch_size 256 --lr 4e-3 --update_freq 2 --model_ema false --model_ema_eval false --use_amp true --data_path /data/benchmarks/ILSVRC2012 --output_dir ./checkpoint \u0026\n\nnohup python -u -m torch.distributed.run --nproc_per_node=8 main.py --model mobilenet_v3_large --epochs 300 --batch_size 256 --lr 4e-3 --update_freq 2 --model_ema false --model_ema_eval false --use_amp true --data_path /data/benchmarks/ILSVRC2012 --output_dir ./checkpoint \u0026\n\nnohup python -u -m torch.distributed.run --nproc_per_node=8 main.py --model mobilenet_v3_large --epochs 450 --batch_size 256 --lr 4e-3 --update_freq 2 --model_ema false --model_ema_eval false --use_amp true --data_path /data/benchmarks/ILSVRC2012 --output_dir ./checkpoint \u0026\n```\n\nThis is a PyTorch implementation of MobileNetV3 architecture as described in the paper [Searching for MobileNetV3](https://arxiv.org/pdf/1905.02244.pdf).\n\nSome details may be different from the original paper, welcome to discuss and help me figure it out.\n\n### MobileNetV3\n|                       | Madds     | Parameters | Top1-acc  |\n| -------------------   | --------- | ---------- | --------- |\n| Small (paper)         | 66  M     | 2.9 M      | 67.4%     |\n| Small (torchvision)   | 62  M     | 2.5 M      | 67.7%     |\n| Small (our 300 epoch) | 69  M     | 3.0 M      | 68.9%     |\n| Small (our 450 epoch) | 69  M     | 3.0 M      | 69.2%     |\n| Large (paper)         | 219  M    | 5.4 M      | 75.2%     |\n| Large (torchvision)   | 235  M    | 5.5 M      | 74.0%     |\n| Large (our 300 epoch) | 241  M    | 5.2 M      | 75.6%     |\n| Large (our 450 epoch) | 241  M    | 5.2 M      | 75.9%     |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxiaolai-sqlai%2Fmobilenetv3","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxiaolai-sqlai%2Fmobilenetv3","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxiaolai-sqlai%2Fmobilenetv3/lists"}