{"id":19243174,"url":"https://github.com/acecoooool/mobilenet-pytorch","last_synced_at":"2025-04-21T09:32:46.908Z","repository":{"id":201607401,"uuid":"148323962","full_name":"AceCoooool/MobileNet-PyTorch","owner":"AceCoooool","description":":star2: This is pytorch implemention of mobile architecture (mobilenet and shufflenet)","archived":false,"fork":false,"pushed_at":"2018-09-13T01:10:21.000Z","size":8,"stargazers_count":8,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-01T12:04:24.809Z","etag":null,"topics":["mobilenet","pytorch"],"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/AceCoooool.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":"2018-09-11T13:43:48.000Z","updated_at":"2024-01-30T16:33:12.000Z","dependencies_parsed_at":null,"dependency_job_id":"081cf5dd-45ed-4b44-9795-022e4f116580","html_url":"https://github.com/AceCoooool/MobileNet-PyTorch","commit_stats":null,"previous_names":["acecoooool/mobilenet-pytorch"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AceCoooool%2FMobileNet-PyTorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AceCoooool%2FMobileNet-PyTorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AceCoooool%2FMobileNet-PyTorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AceCoooool%2FMobileNet-PyTorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AceCoooool","download_url":"https://codeload.github.com/AceCoooool/MobileNet-PyTorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250032232,"owners_count":21363799,"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":["mobilenet","pytorch"],"created_at":"2024-11-09T17:16:54.222Z","updated_at":"2025-04-21T09:32:46.660Z","avatar_url":"https://github.com/AceCoooool.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MobileNet-PyTorch\nThis is pytorch implemention of mobile architecture，converted from [gluon model_zoo](https://github.com/apache/incubator-mxnet/blob/master/python/mxnet/gluon/model_zoo/vision/mobilenet.py)\n\n**Note**：\n\n- The architecture is coming from paper, so the original image size is 224x224 and with rescale=32. however, here use cifar10 as training dataset (image size is 32x32, and resize to 64x64), so the accuracy in this data is not well. (just as demo, so I did not try to modify the architecture)\n- train code is just demo，not compare the architecture\n- The default dataset root in  `your_computer_name/data`\n\n### 1. MobileNet v1\n\nchange  model name：\n\n```python\n# choose network --- choose 0\nmodel_name = ['mobilenet_v1', 'mobilenet_v2', 'shufflenet_v1', 'shufflenet_v2'][0]\n```\n\naccuracy after epoch80：89.48%\n\n### 2. MobileNet v2\n\nchange  model name：\n\n```python\n# choose network --- choose 1\nmodel_name = ['mobilenet_v1', 'mobilenet_v2', 'shufflenet_v1', 'shufflenet_v2'][1]\n```\n\naccuracy after epoch80：89.29%\n\n### 3. ShuffleNet v1\n\nchange  model name：\n\n```python\n# choose network --- choose 2\nmodel_name = ['mobilenet_v1', 'mobilenet_v2', 'shufflenet_v1', 'shufflenet_v2'][2]\n```\n\naccuracy after epoch80：85.44%\n\n### 4. ShuffleNet v2\n\nchange  model name：\n\n```python\n# choose network --- choose 3\nmodel_name = ['mobilenet_v1', 'mobilenet_v2', 'shufflenet_v1', 'shufflenet_v2'][3]\n```\n\naccuracy after epoch80：82.99%\n\n## Reference\n\n1. [gluon model_zoo](https://github.com/apache/incubator-mxnet/blob/master/python/mxnet/gluon/model_zoo/vision/mobilenet.py)：mobilenetv1\u0026v2\n2. [pytorch-cifar](https://github.com/kuangliu/pytorch-cifar/blob/master/models/shufflenet.py)：shufflenet（nearly all the code is copy）","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Facecoooool%2Fmobilenet-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Facecoooool%2Fmobilenet-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Facecoooool%2Fmobilenet-pytorch/lists"}