{"id":15903525,"url":"https://github.com/vfdev-5/layerrotation-pytorch","last_synced_at":"2025-08-25T02:30:47.347Z","repository":{"id":149001244,"uuid":"195516933","full_name":"vfdev-5/LayerRotation-pytorch","owner":"vfdev-5","description":"Layer Rotation experiments in PyTorch","archived":false,"fork":false,"pushed_at":"2019-08-31T22:37:43.000Z","size":762,"stargazers_count":4,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-02T18:11:15.425Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/vfdev-5.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-07-06T08:34:21.000Z","updated_at":"2021-08-26T02:02:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"69c80ecc-f34e-46a4-bba5-9ef824bc6c49","html_url":"https://github.com/vfdev-5/LayerRotation-pytorch","commit_stats":{"total_commits":3,"total_committers":1,"mean_commits":3.0,"dds":0.0,"last_synced_commit":"97ea2ffac0c1f6e33d1b1a3a8c6271eb9823381e"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/vfdev-5/LayerRotation-pytorch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vfdev-5%2FLayerRotation-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vfdev-5%2FLayerRotation-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vfdev-5%2FLayerRotation-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vfdev-5%2FLayerRotation-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vfdev-5","download_url":"https://codeload.github.com/vfdev-5/LayerRotation-pytorch/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vfdev-5%2FLayerRotation-pytorch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":271999291,"owners_count":24856181,"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","status":"online","status_checked_at":"2025-08-25T02:00:12.092Z","response_time":1107,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2024-10-06T12:02:27.843Z","updated_at":"2025-08-25T02:30:46.993Z","avatar_url":"https://github.com/vfdev-5.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Layer Rotation experiments in PyTorch\n\nExperiments on \"Layer Rotation\" indicator and *Layca* applied on Cifar10 dataset.\n\nBased on [\"Layer rotation: a surprisingly powerful indicator of generalization in deep networks?\"](https://arxiv.org/pdf/1806.01603v2.pdf) and paper's [code](https://github.com/ispgroupucl/layer-rotation-tools).\n\n- Layer rotation monitoring (min/mean/max/std over all layers)\n- LAYCA optimizers: \n  - [SGD](code/layca_optims/sgd.py)\n\n\n## Requirements\n\nAll experiments are run [`mlflow`](https://github.com/mlflow/mlflow), please install the latest versions of the library\n```\npip install --upgrade mlflow\n```\n\n## Experiments\n\n### Start MLFlow UI server\n\nPlease create output folder (e.g. `$PWD/output`) and setup mlflow server:\n\n```\nexport OUTPUT_PATH=/path/to/output\n```\nand \n```\nmlflow server --backend-store-uri $OUTPUT_PATH/mlruns --default-artifact-root $OUTPUT_PATH/mlruns -p 5566 -h 0.0.0.0\n```\n\nMLflow dashboard is available in the browser at [0.0.0.0:5566](0.0.0.0:5566)\n\n### CIFAR10 dataset\n\nCreate once \"CIFAR10\" experiment\n```\nexport MLFLOW_TRACKING_URI=$OUTPUT_PATH/mlruns\nmlflow experiments create -n CIFAR10\n```\n\nStart a single run\n\n```\nexport MLFLOW_TRACKING_URI=$OUTPUT_PATH/mlruns\nmlflow run experiments/ --experiment-name=CIFAR10 -P dataset=CIFAR10 -P network=fastresnet -P params=\"with_layca=True;data_path=../input/cifar10;lr_milestones_values=[(0, 0.0), (4, 1.0), (num_epochs, 0.0)]\"\n```\n\n### Tensorboard \n\nAll experiments are also logged to the Tensorboard. To visualize the experiments, please install `tensorboard` and run :\n```\n# tensorboard --logdir=$OUTPUT_PATH/mlruns/\u003cexperiment_id\u003e\ntensorboard --logdir=$OUTPUT_PATH/mlruns/1\n```\n\n![tb_logs](assets/tb_exps.png)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvfdev-5%2Flayerrotation-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvfdev-5%2Flayerrotation-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvfdev-5%2Flayerrotation-pytorch/lists"}