{"id":16360066,"url":"https://github.com/frgfm/pytorch-mnist","last_synced_at":"2026-05-05T19:31:07.931Z","repository":{"id":110056381,"uuid":"147107119","full_name":"frgfm/pytorch-mnist","owner":"frgfm","description":"Implementation of various basic architectures (training on MNIST, Visdom visualization)","archived":false,"fork":false,"pushed_at":"2019-05-05T21:57:28.000Z","size":3104,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-05-21T18:11:30.246Z","etag":null,"topics":["computer-vision","deep-learning","deep-neural-networks","lenet","mnist","python3","pytorch","pytorch-cnn","visdom"],"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/frgfm.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-09-02T17:31:42.000Z","updated_at":"2019-05-05T21:57:29.000Z","dependencies_parsed_at":"2023-04-22T18:04:56.006Z","dependency_job_id":null,"html_url":"https://github.com/frgfm/pytorch-mnist","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/frgfm/pytorch-mnist","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frgfm%2Fpytorch-mnist","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frgfm%2Fpytorch-mnist/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frgfm%2Fpytorch-mnist/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frgfm%2Fpytorch-mnist/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/frgfm","download_url":"https://codeload.github.com/frgfm/pytorch-mnist/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frgfm%2Fpytorch-mnist/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32664717,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-05T11:29:49.557Z","status":"ssl_error","status_checked_at":"2026-05-05T11:29:48.587Z","response_time":54,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["computer-vision","deep-learning","deep-neural-networks","lenet","mnist","python3","pytorch","pytorch-cnn","visdom"],"created_at":"2024-10-11T02:10:28.585Z","updated_at":"2026-05-05T19:31:07.916Z","avatar_url":"https://github.com/frgfm.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Classic architectures on MNIST\nThis repository is an ongoing implementation of different basic DL architectures for Image classification.\nThe implementation is in PyTorch with Visdom support for visualization.\n\n## Installation\nThis project was only developed in Python 3.6 using PyTorch 0.4.1. If you happen to be running a superior version, depending on your edits, you might encounter issue during runtime (breaking changes between Pytorch version).\n```\ngit clone https://github.com/frgfm/pytorch-mnist.git\ncd pytorch-mnist\npip install requirements.txt\n```\n\n## Usage\n\nAdd your architectures (compatible with MNIST 28x28 images) in the architectures folder, and change the net definition accordingly.\n\n### Running the visdom server\nStart the visdom server to visualize your training loss:\n```bash\npython -m visdom.server\n```\nBy default, visdom server will start on port 8097, so navigating to http://localhost:8097 will allow you to see live training results.\n\nIf you happen to perform the training on a remote server, you will need to first allow external connection to this port:\n```bash\nsudo ufw allow 8097\npython -m visdom.server\n```\nThen locally, navigate to `http://\u003cREMOTE_SERVER_IP\u003e:8097` for live training results.\n\n\n### Training your model\nThen open another terminal and run the following command to start training:\n```bash\npython main.py 10 --lr 5e-5 --momentum 0.9 --weight_decay 5e-4 -n --batch_size 8 --gpu 0\n```\nYou can choose the number of epochs, the learning rate, the momentum, the weight decay, whether you wish to use nesterov momentum, the batch size as well as the GPU to use for your training.\n\n![visdom_loss](static/images/lenet5_training.gif)\n\n\n\nIf you wish to resume a training, use the --resume flag\n\n```bash\npython main.py 10 --lr 5e-5 --momentum 0.9 --weight_decay 5e-4 -n --batch_size 8 --gpu 0 --resume Lenet5_checkpoint_best.pth.tar\n```\n\n## TODO\n- [x] LeNet5 implementation\n- [ ] Resuming from checkpoint\n- [ ] Different MLP combinations (+ regularization)\n- [ ] Stop criterion\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffrgfm%2Fpytorch-mnist","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffrgfm%2Fpytorch-mnist","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffrgfm%2Fpytorch-mnist/lists"}