{"id":24493028,"url":"https://github.com/fastmachinelearning/hawq-jet-tagging","last_synced_at":"2025-07-09T07:04:07.259Z","repository":{"id":103769917,"uuid":"536833992","full_name":"fastmachinelearning/hawq-jet-tagging","owner":"fastmachinelearning","description":null,"archived":false,"fork":false,"pushed_at":"2023-11-15T06:45:10.000Z","size":522,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-09T07:02:32.859Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/fastmachinelearning.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":"2022-09-15T02:25:34.000Z","updated_at":"2023-10-31T21:44:29.000Z","dependencies_parsed_at":null,"dependency_job_id":"a868a064-941b-405f-a5ed-6a641f943781","html_url":"https://github.com/fastmachinelearning/hawq-jet-tagging","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/fastmachinelearning/hawq-jet-tagging","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fastmachinelearning%2Fhawq-jet-tagging","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fastmachinelearning%2Fhawq-jet-tagging/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fastmachinelearning%2Fhawq-jet-tagging/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fastmachinelearning%2Fhawq-jet-tagging/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fastmachinelearning","download_url":"https://codeload.github.com/fastmachinelearning/hawq-jet-tagging/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fastmachinelearning%2Fhawq-jet-tagging/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":264411122,"owners_count":23603798,"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":"2025-01-21T19:18:55.356Z","updated_at":"2025-07-09T07:04:07.195Z","avatar_url":"https://github.com/fastmachinelearning.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# hawq-jet-tagging\n\n## Installation\nClone the repository and HAWQ submodule.\n```bash\ngit clone https://github.com/jicampos/hawq-jet-tagging.git\ncd hawq-jet-tagging \ngit submodule init \ngit submodule update \n```\n\nSet up conda environment.\n```bash \nconda env create -f environment.yml\nconda activate hawq-env\n```\n\nDownload [LHC Jet dataset](https://paperswithcode.com/dataset/hls4ml-lhc-jet-dataset).\n```bash\nmkdir dataset\n\nwget https://zenodo.org/record/3602254/files/hls4ml_LHCjet_100p_train.tar.gz -P dataset\nwget https://zenodo.org/record/3602254/files/hls4ml_LHCjet_100p_val.tar.gz -P dataset\n\ntar -zxf dataset/hls4ml_LHCjet_100p_train.tar.gz -C dataset\ntar -zxf dataset/hls4ml_LHCjet_100p_val.tar.gz -C dataset\n```\n\n## Training and Configuration\nPredefined bit configurations are provided under `config` directory. For custom bit configurations, specify the layer name followed by the number of bits inside config files:\n```yaml\nmodel:\n    quant_input: # layer name\n        activation_bit: 6\n    dense_1:     # layer name\n        weight_bit: 8\n        bias_bit: 8\n```\n\nSpecify the bit configuration file using `--config` for training (Default: `config/config_6bit.yml`)\n```bash\npython train_jettagger.py --config config/config_6bit.yml \\\n    --epochs 25 \\\n    --lr 0.01 \\ \n    --data dataset \\\n    --batch-size 1024 \\ \n    --save-path checkpoints\n```\nTo train with Batch Normalization or L1 Regularization, use `--batch-norm` and `--l1`. For all training and logging options, use:\n```bash\npython train_jettagger.py --help\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffastmachinelearning%2Fhawq-jet-tagging","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffastmachinelearning%2Fhawq-jet-tagging","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffastmachinelearning%2Fhawq-jet-tagging/lists"}