{"id":18421955,"url":"https://github.com/spcl/nncompression","last_synced_at":"2025-04-07T14:32:09.135Z","repository":{"id":185473018,"uuid":"542303745","full_name":"spcl/NNCompression","owner":"spcl","description":"Compressing weather and climate data into neural networks","archived":false,"fork":false,"pushed_at":"2024-05-19T16:47:20.000Z","size":35,"stargazers_count":12,"open_issues_count":2,"forks_count":1,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-05-19T17:48:35.381Z","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/spcl.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":"2022-09-27T21:57:12.000Z","updated_at":"2024-05-19T16:47:23.000Z","dependencies_parsed_at":null,"dependency_job_id":"3a637b1a-316a-4d6c-9c98-da820df35a9e","html_url":"https://github.com/spcl/NNCompression","commit_stats":null,"previous_names":["spcl/nncompression"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spcl%2FNNCompression","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spcl%2FNNCompression/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spcl%2FNNCompression/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spcl%2FNNCompression/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/spcl","download_url":"https://codeload.github.com/spcl/NNCompression/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223283933,"owners_count":17119575,"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":"2024-11-06T04:27:25.441Z","updated_at":"2024-11-06T04:27:26.084Z","avatar_url":"https://github.com/spcl.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Download data\nExecute `WeatherBench/download.py` with following arguments:\n```bash\npython download.py --variable=geopotential --mode=single --level_type=pressure --years=2016 --resolution=0.5 --time=00:00 --pressure_level 10 50 100 200 300 400 500 700 850 925 1000 --custom_fn=dataset1.nc\npython download.py --variable=geopotential --mode=single --level_type=pressure --years=2016 --resolution=0.25 --time=00:00 --pressure_level 10 50 100 200 300 400 500 700 850 925 1000 --custom_fn=dataset2.nc\npython download.py --variable=geopotential --mode=separate --level_type=pressure --resolution=5.625 --pressure_level=500 --custom_fn=dataset3_z.nc\npython download.py --variable=temperature --mode=separate --level_type=pressure --resolution=5.625 --pressure_level=850 --custom_fn=dataset3_t.nc\npython download.py --variable=geopotential --mode=separate --level_type=pressure --resolution=2.8125 --pressure_level=500 --custom_fn=dataset4_z.nc\npython download.py --variable=temperature --mode=separate --level_type=pressure --resolution=2.8125 --pressure_level=850 --custom_fn=dataset4_t.nc\n```\n# Run experiments in Section 3.1\n```bash\nfor W in 32 64 128 256 512\ndo\n    python train.py --nepoches=20 --all  --quantizing --testing --variable=z  --dataloader_mode=sampling_nc --file_name=dataset1.nc --width=$W --output_file=dataset1_w${W}.nc\n    python train.py --nepoches=20 --all  --quantizing --testing --variable=z  --dataloader_mode=sampling_nc --file_name=dataset2.nc --width=$W --output_file=dataset2_w${W}.nc\n    python train.py --nepoches=20 --all  --quantizing --generate_full_outputs --variable=z --use_stat --tscale=360 --dataloader_mode=weatherbench  --file_name=dataset3_z_*.nc --width=$W --output_file=dataset3_z_w${W}.nc\n    python train.py --nepoches=20 --all  --quantizing --generate_full_outputs --variable=z --use_stat --tscale=360 --dataloader_mode=weatherbench  --file_name=dataset4_z_*.nc --width=$W --output_file=dataset4_z_w${W}.nc\ndone\n```\n# Compress variables other than geopotential (temperature as an example)\n```bash\npython gen_stat.py --path=\".\" --filename=\"dataset1_w${W}.nc\"\npython gen_stat.py --path=\".\" --filename=\"dataset2_w${W}.nc\"\nfor W in 32 64 128 256 512\ndo\n    python train.py --nepoches=20 --all --use_stat --quantizing --testing --variable=t  --dataloader_mode=sampling_nc --file_name=dataset1.nc --width=$W --output_file=dataset1_w${W}.nc\n    python train.py --nepoches=20 --all --use_stat --quantizing --testing --variable=t  --dataloader_mode=sampling_nc --file_name=dataset2.nc --width=$W --output_file=dataset2_w${W}.nc\ndone\n```\n\n# Run experiments in Section 3.2\n```bash\npython train.py --nepoches=20 --all  --quantizing --generate_full_outputs --variable=z --use_stat --tscale=360 --dataloader_mode=weatherbench  --file_name=dataset4_z_*.nc --width=512 --output_file=dataset4_z_w512.nc\npython train.py --nepoches=20 --all  --quantizing --generate_full_outputs --variable=t --use_stat --tscale=360 --dataloader_mode=weatherbench  --file_name=dataset4_t_*.nc --width=512 --output_file=dataset4_t_w512.nc\ncdo selyear,1979/2015 dataset4_z_w512.nc train_data_path/geopotential_500/geopotential_500_1979_2015.nc\ncdo selyear,2016/2018 dataset4_z.nc train_data_path/geopotential_500/geopotential_500_2016_2018.nc\ncdo selyear,1979/2015 dataset4_t_w512.nc train_data_path/temperature_850/temperature_850_1979_2015.nc\ncdo selyear,2016/2018 dataset4_t.nc train_data_path/temperature_850/temperature_850_2016_2018.nc\ncd WeatherBench\npython -m src.train_nn -c config.yml --datadir=train_data_path\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fspcl%2Fnncompression","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fspcl%2Fnncompression","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fspcl%2Fnncompression/lists"}