Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of fairchem-core

fairchem-core - fairchem-core-2.4.0

What’s Changed

New Features / Enhancements

  • Add OMol evaluations (#1412) @mshuaibii
  • Inference server + client for running local MP graph parallel (#1415) @rayg1234
  • [ BE ] refactored init edge rot mat (#1368) @misko
  • [ BE ] add user accessible embeddings (#1421) @misko
  • diatomic tests (#1429) @wood-b
  • add stress migration option (#1241) @misko
  • enable updating the edges of an AtomicData batch (#1397) @arturtoshev
  • Add inference-only tasks to allow predicting on tasks not trained on (#1411) @rayg1234
  • support eval restarts (#1367) @mshuaibii
  • Load tasks from checkpoint when running benchmarks (#1312) @lbluque
  • bump clusterscope (#1376) @misko
  • add fp64 support (#1337) @misko

Bug Fixes

  • StrEnum backwards compatibility (#1428) @lbluque
  • Modify clamp in radiusgraphpbc (#1303) @ericyuan00000
  • Filter annoying warning (#1413) @rayg1234
  • Fix fine-tuning configs (#1406) @jagritisahoo
  • fix: correct expected value in externalgraphgen error message (True… (#1347) @zulissimeta
  • Fix a bug in AtomicData.toasesingle (#1310) (#1346) @zulissimeta
  • revert lmdb version (#1351) @zulissimeta
  • upgrading clusterscope (#1345) @luccabb
  • if-condition requires pbc is None, but below we index pbc (#1309) (#1314) @arturtoshev

Documentation

  • fix docs, reset calc (#1447) @mshuaibii

Tests

  • added simple so2 tests, impossible vectors test for escn_md, and typehints (#1414) @bkmi

Dependencies

  • Make pymatgen an optional dependency (#1445) @lbluque
  • fix ase version; latest ase is breaking quacc/book build (#1426) @misko
  • revert lmdb version (#1351) @zulissimeta
  • upgrading clusterscope (#1345) @luccabb

- Python
Published by github-actions[bot] 6 months ago

fairchem-core - fairchem_data_omol-0.1.0

What’s Changed

New Features / Enhancements

  • Add release workflows for fairchem-data-omol (#1443) @lbluque
  • omdata cleanup (#1437) @mshuaibii

- Python
Published by github-actions[bot] 6 months ago

fairchem-core - fairchem_data_oc-1.0.2

What’s Changed

New Features / Enhancements

  • ncore=4 (#1381) @mshuaibii

Documentation

  • more style docs tweaks & typos (#1238) @zulissimeta

- Python
Published by github-actions[bot] 6 months ago

fairchem-core - fairchem_applications_cattsunami-1.1.1

What’s Changed

Documentation

  • more style docs tweaks & typos (#1238) @zulissimeta

- Python
Published by github-actions[bot] 6 months ago

fairchem-core - fairchem-core-2.3.0

What’s Changed

Release of UMA-s 1.1 (uma-s-1p1) and UMA-m 1.1 (uma-m-1p1) checkpoints as well as the arxiv paper (https://arxiv.org/abs/2506.23971).

Major changes

  • UMA-m is the best in class model for all tasks across the board.
  • Both Version 1.1 checkpoints fixes a composition bug which made relaxations and simulations on molecular crystals unstable in some cases and violated extensivity property for periodic systems. This fix also improved the accuracy of omol task over v1.0.
  • We also turned off TF32 by default (users can still manually turned it back on for speed) as we were observing it reduced the accuracy of a few property predictions that were highly sensitive to numerical precision (for phonon calculations for example). This will change your results slightly if you upgrade to 2.3.0 and make inference slower, you can switch it back manually by setting tf32=True in the inference_settings.
  • A new simple finetuning procedure has been added.

New Features / Enhancements

  • UMA 1.1 checkpoint release (#1321) @mshuaibii
  • UMA Finetune scripts and docs (#1248) @mshuaibii
  • Dont use tf32 on by default (#1283) @rayg1234
  • Add option to choose cache directory where model is saved (#1264) @suttergustavo
  • adding clusterscope (#1265) @luccabb
  • add option to return checkpoint along with model (#1243) @lbluque
  • assert task datasets is subset of backbone datasets (#1263) @lbluque
  • release isolated atom refs (#1185) @mshuaibii
  • Remove mlipunit specific logic from trainrunner, add Checkpointable protocol (#1233) @rayg1234

Bug Fixes

  • Add osc -> omc migration for non ema checkpoint (#1286) @rayg1234
  • Fix Preemption Checkpointing Mechamism (#1242) @ryanliu30
  • add in model_version to mole and fix composition embebdding (#1258) @misko
  • fix setting implemented properties (#1239) @lbluque

Documentation

  • update FAIRChemCalculator initialization in benchmark configs (#1254) @lbluque
  • more style docs tweaks & typos (#1238) @zulissimeta

- Python
Published by github-actions[bot] 8 months ago

fairchem-core - fairchem_data_oc-1.0.1

What’s Changed

New Features / Enhancements

  • tile solvents (#1106) @mshuaibii

- Python
Published by github-actions[bot] 9 months ago

fairchem-core - fairchem_applications_cattsunami-1.1.0

What’s Changed

Removed OCPNEB to enable fairchemv2 support

Documentation

  • Docs cleanup & molecular info add (#1206) @zulissimeta
  • Fairchemv2 docs update (#1160) @rayg1234

- Python
Published by github-actions[bot] 9 months ago

fairchem-core - fairchem-core-2.2.0

What’s Changed

This version enables batch inference and a variety of bug fixes for the calculator/predictor inference, as well as new documentation

New Features / Enhancements

  • Batch inference cleanup (#1181) @lbluque
  • FAIRChem calculator from_model_checkpoint classmethod (#1203) @lbluque
  • allow automatic device setting when loading mlip predict units (#1202) @lbluque
  • Enable local runs (#1172) @rayg1234

Bug Fixes

  • add pbc v2 grid resolution bounds (#1204) @misko
  • Fix bug when taskname is enum instead of str (#1223) @rayg1234
  • Fix ac mole bug (#1205) @rayg1234

Documentation

  • Docs cleanup & molecular info add (#1206) @zulissimeta
  • version uma (#1199) @mshuaibii

- Python
Published by github-actions[bot] 9 months ago

fairchem-core - fairchem_core-2.1.0

What's Changed

Note fairchem_core-2.1.0 is the first official working pypi package from Fairchem V2. (2.0.0 does not work because it had future dependencies)

New Features

  • pypi ase versions by @mshuaibii in https://github.com/facebookresearch/fairchem/pull/1148
  • move plotting to training only so calculator doesnt use it by @misko in https://github.com/facebookresearch/fairchem/pull/1151
  • Remove a few compile tests by @rayg1234 in https://github.com/facebookresearch/fairchem/pull/1154
  • Replace pytorch geometric with AtomicData by @misko in https://github.com/facebookresearch/fairchem/pull/1156
  • remove lin_ref by @misko in https://github.com/facebookresearch/fairchem/pull/1169
  • Calculator and MLIPPredict unit interface for pretrained models by @lbluque in https://github.com/facebookresearch/fairchem/pull/1153 ### Bug Fixes
  • fix merge for non mole by @misko in https://github.com/facebookresearch/fairchem/pull/1170 ### Documentation
  • Update README.md by @rayg1234 in https://github.com/facebookresearch/fairchem/pull/1141
  • Clean out ESEN/schnet that was suppose be deleted in the merge by @rayg1234 in https://github.com/facebookresearch/fairchem/pull/1150
  • Cleanup evaluation configs by @lbluque in https://github.com/facebookresearch/fairchem/pull/1143
  • update readme and cleanup warnings by @lbluque in https://github.com/facebookresearch/fairchem/pull/1173
  • update README by @lbluque in https://github.com/facebookresearch/fairchem/pull/1174
  • Fairchemv2 docs update by @rayg1234 in https://github.com/facebookresearch/fairchem/pull/1160 ### Tests
  • update PR label checking by @lbluque in https://github.com/facebookresearch/fairchem/pull/1149
  • No test on merge queue by @lbluque in https://github.com/facebookresearch/fairchem/pull/1159 ### Other Changes
  • Update README.md by @lbluque in https://github.com/facebookresearch/fairchem/pull/1144
  • Fix uma speed benchmark script by @misko in https://github.com/facebookresearch/fairchem/pull/1155
  • update adsorbml + neb reqs by @mshuaibii in https://github.com/facebookresearch/fairchem/pull/1158
  • Breakup common utils by @lbluque in https://github.com/facebookresearch/fairchem/pull/1145
  • v2 logo by @mshuaibii in https://github.com/facebookresearch/fairchem/pull/1164
  • Update pyproject.toml by @lbluque in https://github.com/facebookresearch/fairchem/pull/1168

Full Changelog: https://github.com/facebookresearch/fairchem/compare/fairchemcore-2.0.0...fairchemcore-2.1.0

- Python
Published by rayg1234 9 months ago

fairchem-core - fairchem-core-2.1.0

What’s Changed

  • Breakup common utils (#1145) @lbluque
  • Fix uma speed benchmark script (#1155) @misko

New Features / Enhancements

  • Calculator and MLIPPredict unit interface for pretrained models (#1153) @lbluque
  • remove lin_ref (#1169) @misko
  • Replace pytorch geometric with AtomicData (#1156) @misko
  • move plotting to training only so calculator doesnt use it (#1151) @misko
  • pypi ase versions (#1148) @mshuaibii

Bug Fixes

  • fix merge for non mole (#1170) @misko

Documentation

  • update README (#1174) @lbluque
  • update readme and cleanup warnings (#1173) @lbluque
  • Cleanup evaluation configs (#1143) @lbluque
  • Clean out ESEN/schnet that was suppose be deleted in the merge (#1150) @rayg1234

Dependencies

  • Update pyproject.toml (#1168) @lbluque

- Python
Published by github-actions[bot] 9 months ago

fairchem-core - fairchem_applications_cattsunami-1.0.0

What’s Changed

New Features / Enhancements

  • FairchemV2 UMA release 051325 (#1139) @rayg1234

Dependencies

  • update adsorbml + neb reqs (#1158) @mshuaibii

- Python
Published by github-actions[bot] 9 months ago

fairchem-core - fairchem_data_oc-1.0.0

What’s Changed

New Features / Enhancements

  • FairchemV2 UMA release 051325 (#1139) @rayg1234
  • support for direct slab inputs (#1064) @mshuaibii

- Python
Published by github-actions[bot] 9 months ago

fairchem-core - fairchem-core-2.0.0

What’s Changed

New Features / Enhancements

  • FairchemV2 UMA release 051325 (#1139) @rayg1234

- Python
Published by github-actions[bot] 10 months ago

fairchem-core - fairchem-core-1.10.0

What’s Changed

New Features / Enhancements

  • add eSEN model checkpoints to registry (#1115) @lbluque
  • eSEN code release (#1090) @kyonofx
  • remove segmentcsr / segmentcoo dependency (#1052) @misko
  • add check to make sure num_nodes<=1 for local mode (#1091) @misko
  • resolve run_dir to abspath (#1100) @lbluque
  • initialize distributed process with different ports if world size = 1 (#1095) @lbluque

Bug Fixes

  • afterok all run job array jobs (#1103) @lbluque
  • Only initialize logger once (#1104) @lbluque
  • check if submittedpickle exists before attempting to remove runnerstate_path (#1088) @lbluque
  • Graph parallel fix and tests (#1082) @misko
  • always set r_edges to False in OCPCalculator (#1089) @lbluque

Deprecations

  • Switch to upstream LMDB Database (#999) @zulissimeta

Dependencies

  • Switch to upstream LMDB Database (#999) @zulissimeta

- Python
Published by github-actions[bot] 10 months ago

fairchem-core - fairchem-core-1.9.0

What’s Changed

New Features / Enhancements

  • Config descriptors (#1083) @lbluque
  • Add documentation for using quacc with OMat models and huggingface (#1070) @zulissimeta
  • gemnet-oc molecules support (#1075) @mshuaibii
  • Reducer (#1069) @lbluque
  • Add fix gp grad (#1067) @misko
  • wandb log pandas dataframes (#1076) @lbluque

Bug Fixes

  • fix doc deployment (#1084) @zulissimeta
  • Fix tensorboard logger (#1074) @EricZQu
  • PR #1057 Download file to proper location when working in PyPi-installed build (#1058) @levineds

Documentation

  • fix doc deployment (#1084) @zulissimeta
  • Add documentation for using quacc with OMat models and huggingface (#1070) @zulissimeta

Dependencies

  • Adding omitted dependencies to fairchem-core's pyproject.toml (#1043) @Andrew-S-Rosen

- Python
Published by github-actions[bot] 11 months ago

fairchem-core - fairchem_applications_cattsunami-0.3.0

What’s Changed

Bug Fixes

  • OCPNeb fix for finetuned + new trained models (#1013) @mshuaibii
  • Fix OCPNeb trainer loading (#995) @misko

- Python
Published by github-actions[bot] 11 months ago

fairchem-core - fairchem-core-1.8.1

What’s Changed

Bug Fixes

  • Move pickle modification into main rank behind barrier (#1061) @rayg1234

- Python
Published by github-actions[bot] 12 months ago

fairchem-core - fairchem-core-1.7.0

What’s Changed

Dependencies

  • lower huggingfacehub version (#1049) @zulissimeta

- Python
Published by github-actions[bot] 12 months ago

fairchem-core - fairchem-core-1.6.0

What’s Changed

New Features / Enhancements

  • Hf model name download (#1048) @zulissimeta
  • get hash of both core and experimental (#1047) @misko
  • Add disable_amp flag to OCP calculator (#1040) @zulissimeta

Dependencies

  • Hf model name download (#1048) @zulissimeta

- Python
Published by github-actions[bot] 12 months ago

fairchem-core - fairchem-core-1.5.1

What’s Changed

New Features / Enhancements

  • Add results dir for saving full predictions/metrics (#1044) @rayg1234
  • print more specific error on scontrol fail; return cluster unknown (#1039) @misko
  • add error when submitting job from srun/slurm (#1038) @misko

- Python
Published by github-actions[bot] 12 months ago

fairchem-core - fairchem-core-1.5.0

What’s Changed

New Features / Enhancements

  • add graph parallel initialization (#1032) @misko
  • [cli_hydra] Add cluster name to metadata (#1034) @rayg1234
  • add nedges to atoms2graph (#1030) @kyonofx
  • Make preemptions load last found state (#1025) @rayg1234
  • add backbone override to hydra (#997) @misko
  • move two operations to out of place (#1023) @misko
  • Add molecule cell to a2g (#1019) @rayg1234
  • Add profiler callback (#1020) @rayg1234
  • Fix preemption behavior and combine config init (#1016) @rayg1234
  • Remove use of device from bbsampler (#1014) @rayg1234
  • Modify runner and cli for state checkpointing (#1008) @rayg1234
  • Make slurm config separate class (#1006) @rayg1234
  • Add seeds and deterministic mode to Hydra cli (#1002) @rayg1234
  • Allow dataset subset to read in path to rhv (#985) @mshuaibii
  • Strictly enforce no unused keys in yaml (#996) @rayg1234
  • change order of key mapping transform (#993) @misko
  • Add cosine LR, minor edit to hydra cli (#991) @rayg1234
  • Add structured configs to hydra cli, pass cfg to runners (#976) @rayg1234

Bug Fixes

  • sort fix for multiple src (#1037) @mshuaibii
  • Update pyproject to match torch 2.4.x patch versions (#1035) @zulissimeta
  • Fix preemption behavior and combine config init (#1016) @rayg1234
  • astroid<4 (#998) @zulissimeta

Dependencies

  • Update pyproject to match torch 2.4.x patch versions (#1035) @zulissimeta
  • Make slurm config separate class (#1006) @rayg1234
  • astroid<4 (#998) @zulissimeta

- Python
Published by github-actions[bot] about 1 year ago

fairchem-core - fairchem-core-1.4.0

What’s Changed

New Features / Enhancements

  • Add DCP support to main (#938) @rayg1234

Bug Fixes

  • OCPCalculator output_only option (#922) @misko
  • set tensor dtypes and use torch.tensor to initialize tensors in a2g (#935) @lbluque
  • Add cuda set_device for local run (#931) @rayg1234

Dependencies

  • pin pytorch at 240 (#928) @misko

- Python
Published by github-actions[bot] about 1 year ago

fairchem-core - fairchem-core-1.3.0

What’s Changed

New Features / Enhancements

  • EquiformerV2 + DeNS model and trainer (#880) @kyonofx
  • Add wandb logger init to hydra runners (#894) @rayg1234
  • replication use .item(); fix hydra_cli (#920) @kyonofx
  • Add utils for logging weight tables and tensor stats (#907) @rayg1234
  • Rename hydra heads (#903) @lbluque
  • Updated loss and eval metrics (#896) @wood-b
  • add hydra freeze backbone option (#898) @misko
  • Make eqv2 old to hydra converter work with old old configs :'( (#856) @misko
  • Read the logger logging level from environment variable (#874) @misko
  • Add script to make release from fine tuned hydra (#875) @misko
  • Add hydra entrypoint (#867) @rayg1234
  • Add singleton logger (#873) @rayg1234
  • add act checkpointing to escn (#852) @misko
  • throw error when metadata is non integer (#865) @misko
  • change logic to catch missing outputs (#859) @wood-b
  • ESCN export II (#848) @rayg1234
  • enable ruff formatter (#853) @misko

Bug Fixes

  • add ema to BaseTrainer init (#916) @IliasChair
  • Sort paths in datasets (#904) @lbluque
  • remove destroyprocessgroup() from finally wrapper as it can hang (#884) @misko
  • Add tests for hydra gemnet OC scaling factor generation and loading; Raise error on fail to load scaling factors (#831) @misko
  • Match escn_exportable with escn main (#866) @misko
  • fix bug where trainer state not being loaded (#863) @rayg1234

Dependencies

  • update CI tests to py 3.12 (#858) @lbluque
  • bump torch in pyproject.toml (#857) @lbluque

- Python
Published by github-actions[bot] about 1 year ago

fairchem-core - fairchem_data_oc-0.2.0

What’s Changed

Dependencies

  • update CI tests to py 3.12 (#858) @lbluque

- Python
Published by github-actions[bot] about 1 year ago

fairchem-core - fairchem_applications_cattsunami-0.2.0

What’s Changed

Documentation

  • adding tutorial (#882) @brookwander
  • adding link to full dataset (#869) @brookwander

Dependencies

  • bump torch in pyproject.toml (#857) @lbluque

- Python
Published by github-actions[bot] over 1 year ago

fairchem-core - fairchem_demo_ocpapi-0.2.0

What’s Changed

Dependencies

  • ocpapi dependencies / requests -> 2.32.3 (#862) @kjmichel

- Python
Published by github-actions[bot] over 1 year ago

fairchem-core - fairchem-core-1.2.0

What’s Changed

New Features / Enhancements

  • Do not shadow built in property (#841) @lbluque
  • add script to port old equiv2 checkpoint+yaml to hydra version (#846) @misko
  • Delete distributed option - Always use DDP (#833) @rayg1234
  • Torch compile + export escn (#826) @rayg1234
  • Add mean e to escn energy head (#828) @rayg1234
  • add run group (#827) @rayg1234
  • add option to apply mean to energy (#818) @rayg1234
  • fix gemnet scaling factors fit.py and add a test (#819) @misko
  • Add check to max num atoms (#817) @misko
  • Use abs run_dir paths by default (#820) @rayg1234
  • FM-v4 branch into main (#752) @misko
  • refactor and deprecate old equiformerv2 (#812) @misko
  • Fuse all hydras (#814) @rayg1234
  • Rank2 tensor head (#792) @lbluque
  • Explicitly initialize weights even if initialization method is "uniform" (#809) @misko
  • Activation checkpoint equiformersv2 (#811) @rayg1234
  • add resolution flag to escn (#804) @misko

Bug Fixes

  • Add inference_only option to trainers (#850) @lbluque
  • Sort dbs AseDBDataset (#837) @lbluque
  • update to gemnet-oc hydra force head to work with amp (#825) @wood-b
  • Load normalizers patch (#824) @lbluque
  • load linref and normalizer on cuda device when resuming from checkpoint (#813) @misko

- Python
Published by github-actions[bot] over 1 year ago

fairchem-core - fairchem_data_oc-0.1.0

What’s Changed

  • Add solvent interface placement code (#765) @mshuaibii
  • [BE] Remove large files from fairchem and add references to new location as needed (#761) @levineds
  • [BE] Single ruff config (#751) @lbluque
  • calc compatability with new configs (#724) @mshuaibii
  • Package cleanup (#698) @lbluque
  • PyPi CI workflows (#690) @lbluque
  • cattsunami packaging (#678) @lbluque
  • Fixes and updates to the documentation and website (#676) @zulissimeta
  • Consolidate tests into a single folder (#682) @misko
  • GA workflows update (#675) @lbluque
  • Monorepo (#670) @misko

New Features / Enhancements

  • add docstring. Add support for different pseudopotential path (#832) @mshuaibii

Bug Fixes

  • explicitly define ispin for oc20 bulks (#840) @mshuaibii
  • add tags, fix min_ab slab (#829) @mshuaibii

Deprecations

  • Remove large file from repo prior to git history purge (#844) @levineds

- Python
Published by github-actions[bot] over 1 year ago

fairchem-core - fairchem_applications_cattsunami-0.1.0

What’s Changed

  • Fix NEB doc notebooks (#773) @brookwander
  • [BE] Single ruff config (#751) @lbluque
  • calc compatability with new configs (#724) @mshuaibii
  • fixing issue with one reaction (#712) @brookwander
  • adding seed to md tutorial and ipynb (#710) @brookwander
  • Package cleanup (#698) @lbluque
  • fixing summary fig and dissociation scheme fig in the gitbook (#700) @brookwander
  • PyPi CI workflows (#690) @lbluque
  • cattsunami packaging (#678) @lbluque

- Python
Published by github-actions[bot] over 1 year ago

fairchem-core - fairchem_demo_ocpapi-0.1.0

What’s Changed

  • [BE] Single ruff config (#751) @lbluque
  • no ASE version pin (#739) @lbluque
  • move ocpapi to integration tests (#736) @rayg1234
  • Package cleanup (#698) @lbluque
  • PyPi CI workflows (#690) @lbluque
  • Consolidate tests into a single folder (#682) @misko
  • GA workflows update (#675) @lbluque
  • fix ocpapi test (#681) @misko
  • Monorepo (#670) @misko

Dependencies

  • Bump requests from 2.31.0 to 2.32.0 in /packages/fairchem-demo-ocpapi (#707) @dependabot

- Python
Published by github-actions[bot] over 1 year ago

fairchem-core - fairchem_core-1.1.0

What’s Changed

  • Allow symlink'd experimental folder by using absolute and not resolved paths (#798) @zulissimeta
  • fix issues with ddp/hydra and add tests (#796) @misko
  • Wrap atom coordinates in ase.Atoms preprocessing (#783) @kyonofx
  • Add an option to run PBC in single system mode (#795) @misko
  • Move select models to backbone + heads format and add support for hydra (#782) @misko
  • [BE] Remove large files from fairchem and add references to new location as needed (#761) @levineds
  • clone so3 embedding object (#781) @rayg1234
  • add expandable segments var (#775) @rayg1234
  • Fix dataset logic (#771) @lbluque
  • Relax config (#758) @mshuaibii
  • [BE] Single ruff config (#751) @lbluque
  • Make relaxation data more general (#714) @anuroopsriram
  • Add utils to help run torch profiling (#754) @rayg1234
  • Updated ODAC checkpoints & configs (#755) @anuroopsriram
  • Hide wandb.watch behind flag (#747) @rayg1234
  • Try removing importlib - breaks multiprocess pickling (#746) @rayg1234
  • No longer need to specify train dataset loader when predicting (#731) @curtischong
  • Log num params to W&B (#741) @rayg1234
  • Config fix (#737) @lbluque
  • calc compatability with new configs (#724) @mshuaibii
  • update preprocess script (#726) @mshuaibii
  • support logger entity (#717) @mshuaibii
  • pass seed to sampler (#697) @misko

New Features / Enhancements

  • Finetune Hydra (#797) @rayg1234
  • (OTF) Normalization and element references (#715) @lbluque
  • Balanced batch sampler+base dataset (#753) @misko
  • add proxy and ssl support. (#778) @haruyuki-oda
  • Add slurm qos setting (#757) @rayg1234
  • Equiformers2 Graph Parallel (#740) @rayg1234
  • Add option to launch distributed runs locally with >1 GPU (#733) @rayg1234

Bug Fixes

  • Fix job resume on non-preemption type failures (#803) @rayg1234
  • #806: Move data.db to s3 and download via downloadlargefiles (#807) @levineds

Documentation

  • #806: Move data.db to s3 and download via downloadlargefiles (#807) @levineds
  • [BE] lint/test/docs on PR and push to main (#742) @lbluque

Dependencies

  • pin ruff to 0.4.10 (#745) @rayg1234

- Python
Published by github-actions[bot] over 1 year ago

fairchem-core - fairchem_core-1.0.0

New repository structure!

We have restructured our codebase to have all of the FAIR Chemistry's code in one centralized repository of all its data, models, demos, and application efforts.

This release also includes releases for these other namespace packages - fairchemdataoc-0.0.1 - fairchemdemoocpapi-0.0.1 - fairchemapplicationscattsunami-0.0.1

What's Changed

New Features

  • add unique key loader check to YAML to avoid problematic configs by @misko in https://github.com/FAIR-Chem/fairchem/pull/658
  • [BE] PyPi integration + local model cache + Github actions by @misko in https://github.com/FAIR-Chem/fairchem/pull/623
  • [BE] Add smoke test for [escn,gemnet,equiformerv2] train+predict, Add optimization test for [escn,gemnet,equiformerv2] by @misko in https://github.com/FAIR-Chem/fairchem/pull/640 ### Bug Fixes
  • LBFGS batch size fix by @nimashoghi in https://github.com/FAIR-Chem/fairchem/pull/440 ### Other Changes
  • Package scaling dictionary within GemNet-dT pretrained checkpoints by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/419
  • Updates bibtex entries for GemNet-OC, SCN, PaiNN by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/420
  • Update dimenetplusplus to use pyg activation function resolver by @zulissi in https://github.com/FAIR-Chem/fairchem/pull/427
  • Use PBC configuration from ASE atoms objects by @emsunshine in https://github.com/FAIR-Chem/fairchem/pull/429
  • Fixes GPU support with OCPCalculator (refs #424) by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/430
  • Use "deterministic" scatter on CUDA tensors if implemented by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/438
  • Support for using tag weights with L2MAE force loss by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/439
  • Zero out NaNs, if any, in the loss by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/441
  • Updating floating point precision for OC22/total_energy predictions and enabling OC22 challenge submission file generation by @wood-b in https://github.com/FAIR-Chem/fairchem/pull/421
  • fix tag description by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/444
  • Upgrades to pytorch 1.13, cuda 11.6, pyg 2.2.0 by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/442
  • Relaxation storage optimizations by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/445
  • Support dataset sharding by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/446
  • Catch OOM during relaxations by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/447
  • Improper OOM merge fix by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/451
  • Warnings for missing scale files during validation by @zulissimeta in https://github.com/FAIR-Chem/fairchem/pull/450
  • SCN checkpoint release + missing AdsorbML checkpoints by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/453
  • Adds scaling factors to GNOC-All-MD checkpoint and updates paths for some checkpoints by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/456
  • Updating flags and docs for training on total energy targets by @wood-b in https://github.com/FAIR-Chem/fairchem/pull/455
  • eSCN checkpoints+configs by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/457
  • eSCN CPU support by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/465
  • LMDB folder fix by @zulissimeta in https://github.com/FAIR-Chem/fairchem/pull/476
  • Revert "LMDB folder fix" by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/480
  • Allow models to include degenerate edges by @emsunshine in https://github.com/FAIR-Chem/fairchem/pull/467
  • Adds init files to enable portability with pip install without the -e flag by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/490
  • Adds GemNet-OC checkpoint trained on OC20+OC22 total energies with enforce_max_neighbors_strictly=False by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/495
  • Fixes #501: don't cast a jagged list as np.array by @zulissimeta in https://github.com/FAIR-Chem/fairchem/pull/500
  • Maintenance updates by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/506
  • clarify lmdb creation in tutorial by @brookwander in https://github.com/FAIR-Chem/fairchem/pull/509
  • Add ASE Datasets by @emsunshine in https://github.com/FAIR-Chem/fairchem/pull/492
  • LMDB-based ASE dataset, generic targets, target metadata guessing by @zulissimeta in https://github.com/FAIR-Chem/fairchem/pull/513
  • Add type annotations by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/519
  • Add more type annotations by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/522
  • eSCN cpu fix by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/523
  • EquiformerV2 support by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/518
  • Add isort to CI by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/527
  • ocp calc amp fix by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/529
  • Remove unused imports and sort imports by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/528
  • Skipping scheduler setup in EquiformerV2 trainer if train_loader isn't defined by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/541
  • Add autoflake to pre-commit to eliminate unused imports automatically by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/534
  • More type annotations by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/544
  • Add more types, handle empty registries gracefully by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/545
  • More type annotations by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/546
  • Use logging instead of print by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/551
  • More type annotations by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/548
  • Bug Fixes for Tutorial by @emsunshine in https://github.com/FAIR-Chem/fairchem/pull/525
  • Typecast scheduler params to int + fix slurm experiment logging by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/555
  • Adds a unit test for using OCP models with the ASE calculator by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/565
  • Fixes typo in loading checkpoints in BaseTrainer by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/567
  • Fixes Codecov badge URL by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/568
  • Adds boolean for whether to use strict max_neighbors in EquiformerV2 by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/571
  • GemNet-GP dense layer bugfix (fixes #573) by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/574
  • Adds an FAQ by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/564
  • Type fixes for using the MultistepLR scheduler by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/578
  • [Minor] Support for passing in stats to Equiformer V2 model by @anuroopsriram in https://github.com/FAIR-Chem/fairchem/pull/576
  • Support IS2RE-Direct Training with ASE Read Datasets by @emsunshine in https://github.com/FAIR-Chem/fairchem/pull/579
  • Fixes nested YAML config loading from the ASE calculator by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/585
  • Adds optional per-element linear reference coefficients to EquiformerV2 by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/584
  • Release EquiformerV2 checkpoint trained on OC22 by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/586
  • Changes for ODAC Release by @anuroopsriram in https://github.com/FAIR-Chem/fairchem/pull/588
  • Update odac data link by @anuroopsriram in https://github.com/FAIR-Chem/fairchem/pull/595
  • Update EqV2 31M ODAC checkpoint by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/599
  • Add natoms to ASE datasets by @emsunshine in https://github.com/FAIR-Chem/fairchem/pull/598
  • DDEC release and IS2RS clarification for ODAC23 by @anuroopsriram in https://github.com/FAIR-Chem/fairchem/pull/602
  • Unified OCP Trainer by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/520
  • Fix edgeindex check in makelmdb_sizes.py by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/611
  • cleanup+documentation by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/615
  • fix config spacing by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/616
  • Set default val and test dataset class to be same as train by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/618
  • bump miniconda version by @misko in https://github.com/FAIR-Chem/fairchem/pull/627
  • Fix amp scale factor for loss by @janiceblue in https://github.com/FAIR-Chem/fairchem/pull/617
  • Release ODAC23 data in extxyz format by @anuroopsriram in https://github.com/FAIR-Chem/fairchem/pull/625
  • add seed option for calculator by @misko in https://github.com/FAIR-Chem/fairchem/pull/624
  • Add in tests for coefficient mapping, mprimary, lprimary by @misko in https://github.com/FAIR-Chem/fairchem/pull/626
  • Minor fix in run_relaxations by @AdeeshKolluru in https://github.com/FAIR-Chem/fairchem/pull/636
  • Ase dataset updates by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/622
  • add step(batch) stateful sampler by @misko in https://github.com/FAIR-Chem/fairchem/pull/639
  • Add warning and optimize sampler per @lbluque suggestion by @misko in https://github.com/FAIR-Chem/fairchem/pull/642
  • lin ref in ase datasets by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/643
  • change computemetrics not to modify callers version by @misko in https://github.com/FAIR-Chem/fairchem/pull/645
  • [BE] Set weights and biases as default logger by @janiceblue in https://github.com/FAIR-Chem/fairchem/pull/647
  • Invert experimental import logic to opt-in by @levineds in https://github.com/FAIR-Chem/fairchem/pull/651
  • do not add empty lines to include_dirs by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/656
  • [BE] Upgrade all dependencies by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/654
  • Monorepo by @misko in https://github.com/FAIR-Chem/fairchem/pull/670
  • fix install order in env.gpu.yml so pyg does not mess things up by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/673
  • fix ocp readme links by @misko in https://github.com/FAIR-Chem/fairchem/pull/679
  • fix ocpapi test by @misko in https://github.com/FAIR-Chem/fairchem/pull/681
  • make conda cpu env name consistent with gpu version by @misko in https://github.com/FAIR-Chem/fairchem/pull/683
  • GA workflows update by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/675
  • Update main readme by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/686
  • logo colors by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/687
  • Consolidate tests into a single folder by @misko in https://github.com/FAIR-Chem/fairchem/pull/682
  • Fixes and updates to the documentation and website by @zulissimeta in https://github.com/FAIR-Chem/fairchem/pull/676
  • Bump actions/setup-python from 4 to 5 by @dependabot in https://github.com/FAIR-Chem/fairchem/pull/689
  • cattsunami packaging by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/678
  • Small fixes to make tutorial notebooks pass by @misko in https://github.com/FAIR-Chem/fairchem/pull/688
  • PyPi CI workflows by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/690
  • add windows install instructions by @misko in https://github.com/FAIR-Chem/fairchem/pull/692
  • change cattsunami autoapi and skip ocpapi execution from docs by @misko in https://github.com/FAIR-Chem/fairchem/pull/693
  • fix dist paths in release workflow by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/695
  • simplify calc usage by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/694
  • skip ocpapi integration tests in default test workflow by @misko in https://github.com/FAIR-Chem/fairchem/pull/696
  • adding pages for oc20dense and oc20neb by @brookwander in https://github.com/FAIR-Chem/fairchem/pull/699
  • reorganize toc by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/701
  • fixing summary fig and dissociation scheme fig in the gitbook by @brookwander in https://github.com/FAIR-Chem/fairchem/pull/700
  • Package cleanup by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/698
  • update install instructions by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/702
  • cleanup amp warning by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/703
  • Fix doc install typos by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/704

New Contributors

  • @r-barnes made their first contribution in https://github.com/FAIR-Chem/fairchem/pull/519
  • @misko made their first contribution in https://github.com/FAIR-Chem/fairchem/pull/627
  • @janiceblue made their first contribution in https://github.com/FAIR-Chem/fairchem/pull/617
  • @levineds made their first contribution in https://github.com/FAIR-Chem/fairchem/pull/651
  • @dependabot made their first contribution in https://github.com/FAIR-Chem/fairchem/pull/689

Full Changelog: https://github.com/FAIR-Chem/fairchem/compare/v0.1.0...fairchem_core-1.0.0

- Python
Published by lbluque almost 2 years ago

fairchem-core - fairchem_core-1.0.0b0

What's Changed

New Features

  • add unique key loader check to YAML to avoid problematic configs by @misko in https://github.com/FAIR-Chem/fairchem/pull/658
  • [BE] PyPi integration + local model cache + Github actions by @misko in https://github.com/FAIR-Chem/fairchem/pull/623
  • [BE] Add smoke test for [escn,gemnet,equiformerv2] train+predict, Add optimization test for [escn,gemnet,equiformerv2] by @misko in https://github.com/FAIR-Chem/fairchem/pull/640 ### Bug Fixes
  • LBFGS batch size fix by @nimashoghi in https://github.com/FAIR-Chem/fairchem/pull/440 ### Other Changes
  • Package scaling dictionary within GemNet-dT pretrained checkpoints by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/419
  • Updates bibtex entries for GemNet-OC, SCN, PaiNN by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/420
  • Update dimenetplusplus to use pyg activation function resolver by @zulissi in https://github.com/FAIR-Chem/fairchem/pull/427
  • Use PBC configuration from ASE atoms objects by @emsunshine in https://github.com/FAIR-Chem/fairchem/pull/429
  • Fixes GPU support with OCPCalculator (refs #424) by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/430
  • Use "deterministic" scatter on CUDA tensors if implemented by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/438
  • Support for using tag weights with L2MAE force loss by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/439
  • Zero out NaNs, if any, in the loss by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/441
  • Updating floating point precision for OC22/total_energy predictions and enabling OC22 challenge submission file generation by @wood-b in https://github.com/FAIR-Chem/fairchem/pull/421
  • fix tag description by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/444
  • Upgrades to pytorch 1.13, cuda 11.6, pyg 2.2.0 by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/442
  • Relaxation storage optimizations by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/445
  • Support dataset sharding by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/446
  • Catch OOM during relaxations by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/447
  • Improper OOM merge fix by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/451
  • Warnings for missing scale files during validation by @zulissimeta in https://github.com/FAIR-Chem/fairchem/pull/450
  • SCN checkpoint release + missing AdsorbML checkpoints by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/453
  • Adds scaling factors to GNOC-All-MD checkpoint and updates paths for some checkpoints by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/456
  • Updating flags and docs for training on total energy targets by @wood-b in https://github.com/FAIR-Chem/fairchem/pull/455
  • eSCN checkpoints+configs by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/457
  • eSCN CPU support by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/465
  • LMDB folder fix by @zulissimeta in https://github.com/FAIR-Chem/fairchem/pull/476
  • Revert "LMDB folder fix" by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/480
  • Allow models to include degenerate edges by @emsunshine in https://github.com/FAIR-Chem/fairchem/pull/467
  • Adds init files to enable portability with pip install without the -e flag by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/490
  • Adds GemNet-OC checkpoint trained on OC20+OC22 total energies with enforce_max_neighbors_strictly=False by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/495
  • Fixes #501: don't cast a jagged list as np.array by @zulissimeta in https://github.com/FAIR-Chem/fairchem/pull/500
  • Maintenance updates by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/506
  • clarify lmdb creation in tutorial by @brookwander in https://github.com/FAIR-Chem/fairchem/pull/509
  • Add ASE Datasets by @emsunshine in https://github.com/FAIR-Chem/fairchem/pull/492
  • LMDB-based ASE dataset, generic targets, target metadata guessing by @zulissimeta in https://github.com/FAIR-Chem/fairchem/pull/513
  • Add type annotations by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/519
  • Add more type annotations by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/522
  • eSCN cpu fix by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/523
  • EquiformerV2 support by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/518
  • Add isort to CI by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/527
  • ocp calc amp fix by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/529
  • Remove unused imports and sort imports by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/528
  • Skipping scheduler setup in EquiformerV2 trainer if train_loader isn't defined by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/541
  • Add autoflake to pre-commit to eliminate unused imports automatically by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/534
  • More type annotations by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/544
  • Add more types, handle empty registries gracefully by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/545
  • More type annotations by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/546
  • Use logging instead of print by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/551
  • More type annotations by @r-barnes in https://github.com/FAIR-Chem/fairchem/pull/548
  • Bug Fixes for Tutorial by @emsunshine in https://github.com/FAIR-Chem/fairchem/pull/525
  • Typecast scheduler params to int + fix slurm experiment logging by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/555
  • Adds a unit test for using OCP models with the ASE calculator by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/565
  • Fixes typo in loading checkpoints in BaseTrainer by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/567
  • Fixes Codecov badge URL by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/568
  • Adds boolean for whether to use strict max_neighbors in EquiformerV2 by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/571
  • GemNet-GP dense layer bugfix (fixes #573) by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/574
  • Adds an FAQ by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/564
  • Type fixes for using the MultistepLR scheduler by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/578
  • [Minor] Support for passing in stats to Equiformer V2 model by @anuroopsriram in https://github.com/FAIR-Chem/fairchem/pull/576
  • Support IS2RE-Direct Training with ASE Read Datasets by @emsunshine in https://github.com/FAIR-Chem/fairchem/pull/579
  • Fixes nested YAML config loading from the ASE calculator by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/585
  • Adds optional per-element linear reference coefficients to EquiformerV2 by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/584
  • Release EquiformerV2 checkpoint trained on OC22 by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/586
  • Changes for ODAC Release by @anuroopsriram in https://github.com/FAIR-Chem/fairchem/pull/588
  • Update odac data link by @anuroopsriram in https://github.com/FAIR-Chem/fairchem/pull/595
  • Update EqV2 31M ODAC checkpoint by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/599
  • Add natoms to ASE datasets by @emsunshine in https://github.com/FAIR-Chem/fairchem/pull/598
  • DDEC release and IS2RS clarification for ODAC23 by @anuroopsriram in https://github.com/FAIR-Chem/fairchem/pull/602
  • Unified OCP Trainer by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/520
  • Fix edgeindex check in makelmdb_sizes.py by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/611
  • cleanup+documentation by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/615
  • fix config spacing by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/616
  • Set default val and test dataset class to be same as train by @abhshkdz in https://github.com/FAIR-Chem/fairchem/pull/618
  • bump miniconda version by @misko in https://github.com/FAIR-Chem/fairchem/pull/627
  • Fix amp scale factor for loss by @janiceblue in https://github.com/FAIR-Chem/fairchem/pull/617
  • Release ODAC23 data in extxyz format by @anuroopsriram in https://github.com/FAIR-Chem/fairchem/pull/625
  • add seed option for calculator by @misko in https://github.com/FAIR-Chem/fairchem/pull/624
  • Add in tests for coefficient mapping, mprimary, lprimary by @misko in https://github.com/FAIR-Chem/fairchem/pull/626
  • Minor fix in run_relaxations by @AdeeshKolluru in https://github.com/FAIR-Chem/fairchem/pull/636
  • Ase dataset updates by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/622
  • add step(batch) stateful sampler by @misko in https://github.com/FAIR-Chem/fairchem/pull/639
  • Add warning and optimize sampler per @lbluque suggestion by @misko in https://github.com/FAIR-Chem/fairchem/pull/642
  • lin ref in ase datasets by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/643
  • change computemetrics not to modify callers version by @misko in https://github.com/FAIR-Chem/fairchem/pull/645
  • [BE] Set weights and biases as default logger by @janiceblue in https://github.com/FAIR-Chem/fairchem/pull/647
  • Invert experimental import logic to opt-in by @levineds in https://github.com/FAIR-Chem/fairchem/pull/651
  • do not add empty lines to include_dirs by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/656
  • [BE] Upgrade all dependencies by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/654
  • Monorepo by @misko in https://github.com/FAIR-Chem/fairchem/pull/670
  • fix install order in env.gpu.yml so pyg does not mess things up by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/673
  • fix ocp readme links by @misko in https://github.com/FAIR-Chem/fairchem/pull/679
  • fix ocpapi test by @misko in https://github.com/FAIR-Chem/fairchem/pull/681
  • make conda cpu env name consistent with gpu version by @misko in https://github.com/FAIR-Chem/fairchem/pull/683
  • GA workflows update by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/675
  • Update main readme by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/686
  • logo colors by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/687
  • Consolidate tests into a single folder by @misko in https://github.com/FAIR-Chem/fairchem/pull/682
  • Fixes and updates to the documentation and website by @zulissimeta in https://github.com/FAIR-Chem/fairchem/pull/676
  • Bump actions/setup-python from 4 to 5 by @dependabot in https://github.com/FAIR-Chem/fairchem/pull/689
  • cattsunami packaging by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/678
  • Small fixes to make tutorial notebooks pass by @misko in https://github.com/FAIR-Chem/fairchem/pull/688
  • PyPi CI workflows by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/690
  • add windows install instructions by @misko in https://github.com/FAIR-Chem/fairchem/pull/692
  • change cattsunami autoapi and skip ocpapi execution from docs by @misko in https://github.com/FAIR-Chem/fairchem/pull/693
  • fix dist paths in release workflow by @lbluque in https://github.com/FAIR-Chem/fairchem/pull/695
  • simplify calc usage by @mshuaibii in https://github.com/FAIR-Chem/fairchem/pull/694
  • skip ocpapi integration tests in default test workflow by @misko in https://github.com/FAIR-Chem/fairchem/pull/696

New Contributors

  • @r-barnes made their first contribution in https://github.com/FAIR-Chem/fairchem/pull/519
  • @misko made their first contribution in https://github.com/FAIR-Chem/fairchem/pull/627
  • @janiceblue made their first contribution in https://github.com/FAIR-Chem/fairchem/pull/617
  • @levineds made their first contribution in https://github.com/FAIR-Chem/fairchem/pull/651
  • @dependabot made their first contribution in https://github.com/FAIR-Chem/fairchem/pull/689

Full Changelog: https://github.com/FAIR-Chem/fairchem/compare/v0.1.0...fairchem_core-1.0.0b0

- Python
Published by lbluque almost 2 years ago

fairchem-core - v0.1.0

Major features and improvements

  • Release of the OC22 dataset (https://github.com/Open-Catalyst-Project/ocp/pull/358) focused on oxide electrocatalysis (paper, blog) and pretrained model weights (https://github.com/Open-Catalyst-Project/ocp/pull/414)
  • GemNet-OC implementation and pretrained model weights (https://github.com/Open-Catalyst-Project/ocp/pull/363) (paper)
  • Spherical Channel Network implementation (https://github.com/Open-Catalyst-Project/ocp/pull/362) (paper)
  • OC20 Bader charge data (https://github.com/Open-Catalyst-Project/ocp/pull/360)
  • PaiNN implementation and pretrained model weights (https://github.com/Open-Catalyst-Project/ocp/pull/344) (paper)
  • OCP tutorial (https://github.com/Open-Catalyst-Project/ocp/pull/314, https://github.com/Open-Catalyst-Project/ocp/pull/265)
  • Script to render relaxation trajectory GIFs (https://github.com/Open-Catalyst-Project/ocp/pull/259)
  • Load balancing batches across GPUs (https://github.com/Open-Catalyst-Project/ocp/pull/267, https://github.com/Open-Catalyst-Project/ocp/pull/277)
  • Support for cutoff radius beyond 1 unit cell across all directions in radius_graph_pbc (https://github.com/Open-Catalyst-Project/ocp/pull/268, https://github.com/Open-Catalyst-Project/ocp/pull/394)
  • Support for evaluating relaxations during S2EF training (https://github.com/Open-Catalyst-Project/ocp/pull/299)
  • Up to 5x speedup in running relaxations (https://github.com/Open-Catalyst-Project/ocp/pull/309)
  • 25% reduction in memory usage for inference of direct-force models (https://github.com/Open-Catalyst-Project/ocp/pull/323)
  • Atomwise L2 loss (https://github.com/Open-Catalyst-Project/ocp/pull/343, https://github.com/Open-Catalyst-Project/ocp/pull/346)

Breaking changes

  • DimeNet++ triplet calculation fix (https://github.com/Open-Catalyst-Project/ocp/pull/270)
    • This breaks backward compatibility to previously trained DimeNet++ models, though the change in performance is very small (< 0.5% relative).

Other changes

  • Support for ignoring specified directories within experimental by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/257
  • bugfix: remove epoch arg from validate by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/261
  • Import logger when setting up imports; fixes #262 by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/263
  • setup v3 by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/264
  • bugfix: update model name in gemnet fit_scaling by @wood-b in https://github.com/Open-Catalyst-Project/ocp/pull/274
  • Reduce testcosinesimilarity check to 2 decimals by @gasteigerjo in https://github.com/Open-Catalyst-Project/ocp/pull/276
  • Makes Ray Tune optional and fixes submitit checkpointing bug by @wood-b in https://github.com/Open-Catalyst-Project/ocp/pull/272
  • add missing spinconv import by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/278
  • challenge submission script by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/279
  • Correctly calculate distributed loss average by @gasteigerjo in https://github.com/Open-Catalyst-Project/ocp/pull/269
  • Adds download link to the challenge dataset by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/281
  • explicit cpu map by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/282
  • missing spinconv device definition by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/285
  • Fix shared parameter gradient scaling by @gasteigerjo in https://github.com/Open-Catalyst-Project/ocp/pull/283
  • update oc20 data mapping by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/288
  • bugfix loading best_checkpoint.pt by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/289
  • bugfix: checkpoint with no val set Ref. #290 by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/291
  • add data-path arg to download script by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/294
  • Changed default trainer to energy by @AdeeshKolluru in https://github.com/Open-Catalyst-Project/ocp/pull/298
  • Loads checkpoint cleanly for non DDP checkpoint and parallelized inference by @AdeeshKolluru in https://github.com/Open-Catalyst-Project/ocp/pull/295
  • Updated OCPCalculator to not require config and data paths by @AdeeshKolluru in https://github.com/Open-Catalyst-Project/ocp/pull/297
  • Added modified K-hot elemental embeddings from QMOF CGCNN repo (QMOFKHOTEMBEDDINGS) by @EricMusa in https://github.com/Open-Catalyst-Project/ocp/pull/296
  • change circle resource class by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/305
  • swap checksums by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/303
  • OCPCalc Update: uses otf_graph by default and takes in dictionary as well by @AdeeshKolluru in https://github.com/Open-Catalyst-Project/ocp/pull/304
  • Hotfix: Turns otf_graph True for OCPCalc by @AdeeshKolluru in https://github.com/Open-Catalyst-Project/ocp/pull/306
  • Fixed logger_project config not working by @nimashoghi in https://github.com/Open-Catalyst-Project/ocp/pull/301
  • Adds SpinConv, GemNet-dT checkpoints trained on S2EF-2M by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/308
  • no-pbc gemnet support by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/311
  • remove ipynb from language stats by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/318
  • demjson env fix by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/321
  • Added support for PyTorch Geometric 2.0's updated Data format by @nimashoghi in https://github.com/Open-Catalyst-Project/ocp/pull/316
  • PyTorch 1.9.0 by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/322
  • add universal dataset reader by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/310
  • Updates RandomRotate to return correct rotation matrices following PyG bugfix by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/325
  • Log unused parameter names on DDP errors by @nimashoghi in https://github.com/Open-Catalyst-Project/ocp/pull/317
  • PyG 2 Support Regression by @nimashoghi in https://github.com/Open-Catalyst-Project/ocp/pull/327
  • Update conditional_grad decorator to use functools.wraps on the original function by @nimashoghi in https://github.com/Open-Catalyst-Project/ocp/pull/326
  • bugfix for dict dataset definition by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/329
  • Added an option to disable DDP for relaxations by @anuroopsriram in https://github.com/Open-Catalyst-Project/ocp/pull/312
  • OCPCalculator CUDA support by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/333
  • gemnet scaling script fix by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/339
  • Removes extra context on GPU0 for distributed training by @wood-b in https://github.com/Open-Catalyst-Project/ocp/pull/342
  • Bugfix in best val metric check for checkpointing by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/345
  • Readme update by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/347
  • Make sure best val metric is loaded when restoring checkpoint by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/349
  • bugfix PR#343 by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/351
  • Update environment installation by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/352
  • fix to gemnet scaling.py to detect if file does not exist and proceed… by @jmusiel in https://github.com/Open-Catalyst-Project/ocp/pull/340
  • Fixing celloffsets error in DimeNet++ for usepbc=False and otf_graph=False by @aarongarrison in https://github.com/Open-Catalyst-Project/ocp/pull/350
  • Bugfix to #349 by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/353
  • Make sure posrelaxed and yrelaxed are not None in val run_relaxations by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/356
  • Correct OC22 download address by @KruskalLin in https://github.com/Open-Catalyst-Project/ocp/pull/361
  • Additional OC22 configs + example configs by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/359
  • Remove old is_vis flag from fit_scaling by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/365
  • Bugfix: Data created with PyG>2.0 by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/367
  • Catch missing edge_index TypeError in datalistcollater (+ suppress a few // warnings) by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/368
  • GemNet-OC readme with test metrics by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/369
  • Implementation of graph parallel training by @anuroopsriram in https://github.com/Open-Catalyst-Project/ocp/pull/364
  • Relay keyword arguments through from OCPDataParallel to the model by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/370
  • Covers all checkpoint loading mismatch possibilities by @AdeeshKolluru in https://github.com/Open-Catalyst-Project/ocp/pull/371
  • Log correct job id for slurm arrays by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/372
  • Fixes PaiNN's stability issues by @AdeeshKolluru in https://github.com/Open-Catalyst-Project/ocp/pull/373
  • Circle CI - merge conda install and create env runs by @AdeeshKolluru in https://github.com/Open-Catalyst-Project/ocp/pull/374
  • Adds otf_graph flag for GemNet-OC by @AdeeshKolluru in https://github.com/Open-Catalyst-Project/ocp/pull/377
  • Consistent graph generation implementation across models by @AdeeshKolluru in https://github.com/Open-Catalyst-Project/ocp/pull/378
  • Throw error if scale file is missing for GemNet-OC by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/380
  • Bugfix: restore original params when predict is called with per_image == False by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/381
  • Make OCPCalculator support both list and dict dataset configs by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/382
  • Set tags in AtomsToGraphs since GemNet models need it for inference by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/385
  • Load attached scale file by @jmusiel in https://github.com/Open-Catalyst-Project/ocp/pull/386
  • Bugfix: use correct otfgraph, cutoff, maxneighbors for GemNet-OC graphs by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/387
  • Load scaling factors from checkpoint if available by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/388
  • Bugfix: use correct offset distances in DimeNet, DimeNet++ by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/391
  • Absolute registry import paths by @nimashoghi in https://github.com/Open-Catalyst-Project/ocp/pull/315
  • Added better/more legible registry import errors by @nimashoghi in https://github.com/Open-Catalyst-Project/ocp/pull/398
  • Unit test for GemNet-OC by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/393
  • Snapshot testing using syrupy by @nimashoghi in https://github.com/Open-Catalyst-Project/ocp/pull/399
  • Windows fixes by @nimashoghi in https://github.com/Open-Catalyst-Project/ocp/pull/401
  • Revert to older / faster implementation of wigner_D in e3nn.o3 by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/402
  • Explicitly check e3nn == 0.2.6 when running SCN by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/404
  • Integrates codecov by @abhshkdz in https://github.com/Open-Catalyst-Project/ocp/pull/403
  • New scaling module by @nimashoghi in https://github.com/Open-Catalyst-Project/ocp/pull/390
  • Fix pre-empt recovery crash by @nimashoghi in https://github.com/Open-Catalyst-Project/ocp/pull/407
  • Remove Python 3.8 only fstring interpolations by @nimashoghi in https://github.com/Open-Catalyst-Project/ocp/pull/411
  • reduce macos resource class by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/415
  • Balanced batch sampler fix by @nimashoghi in https://github.com/Open-Catalyst-Project/ocp/pull/406
  • Include more thorough tests in testradiusgraph_pbc by @emsunshine in https://github.com/Open-Catalyst-Project/ocp/pull/410
  • alt trainer identifier by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/416
  • OCPCalc edge cases by @mshuaibii in https://github.com/Open-Catalyst-Project/ocp/pull/417

New Contributors

  • @AdeeshKolluru made their first contribution in https://github.com/Open-Catalyst-Project/ocp/pull/259
  • @gasteigerjo made their first contribution in https://github.com/Open-Catalyst-Project/ocp/pull/276
  • @EricMusa made their first contribution in https://github.com/Open-Catalyst-Project/ocp/pull/296
  • @nimashoghi made their first contribution in https://github.com/Open-Catalyst-Project/ocp/pull/301
  • @jmusiel made their first contribution in https://github.com/Open-Catalyst-Project/ocp/pull/340
  • @aarongarrison made their first contribution in https://github.com/Open-Catalyst-Project/ocp/pull/350
  • @KruskalLin made their first contribution in https://github.com/Open-Catalyst-Project/ocp/pull/361
  • @emsunshine made their first contribution in https://github.com/Open-Catalyst-Project/ocp/pull/394

Full Changelog: https://github.com/Open-Catalyst-Project/ocp/compare/v0.0.3...v0.1.0

- Python
Published by abhshkdz over 3 years ago

fairchem-core - v0.0.3: GemNet-dT, SpinConv, new data: MD, Rattled, per-adsorbate trajectories, etc.

Breaking changes

  • Scheduler changed to step every iteration (#234). If your config specifies lr_milestones or warmup_epochs in epochs instead of steps, this will change how your scheduler behaves.
  • OCPCalculator no longer takes in a Trainer class as input. Instead, a yaml file and checkpoint path must be provided.

Major features

  • GemNet-dT implementation and pretrained model (following https://arxiv.org/abs/2106.08903). This is now the best-performing model across all OCP tasks (see leaderboards).
  • SpinConv implementation and pretrained model (following https://arxiv.org/abs/2106.09575)
  • DimeNet++ pretrained models (#200), updated IS2RE models (#203)
  • ~2x reduction in GPU memory usage during inference (#199, #201)
  • Per-adsorbate trajectory datasets (#225)
  • Rattled / MD datasets (#224)
  • IS2RE relaxation scripts; relevant for NeurIPS ‘21 challenge participants (#253)

Other changes and improvements

  • Support for Python 3.8, PyTorch 1.8.1 (#247)
  • Early stopping for ML relaxations
  • Support for gradient clipping and maintaining an exponential moving average of parameters
  • Preprocessing support for datasets that do not have fixed atoms specified (#189)
  • Jupyter notebooks for creating LMDBs on your own data, understanding the data preprocessing pipeline (#211)
  • Release cached CUDA memory after each relaxation batch (#190)
  • Security fix in loading EvalAI npz submissions (#194)
  • Dataloader bug fix for when #GPUs > #LMDBs (#248)
  • Support for custom optimizers (#218)
  • Support for custom schedulers (#226)
  • New attributes (miller_index, shift, adsorption site, etc.) in data mapping (#219)
  • Deterministic unit tests (#228)
  • Bug fixes in released data for all tasks / splits (#197)
  • Improved logs: using logging instead of print commands, recording slurm settings
  • Better handling of job resumption on pre-emption; particularly relevant for those using slurm-based clusters. Model weights and training state are now saved to separate checkpoints, and all restarted jobs log to the same wandb plot instead of a new plot per restart.
  • Support for energy-only predictions in OCPCalculator (#243)

- Python
Published by abhshkdz over 4 years ago

fairchem-core - v0.0.2: DimeNet++, ForceNet, Torch relaxations, model zoo, etc.

This release accompanies v2 of the OCP dataset paper.

Major features

  • DimeNet++ IS2RE and S2EF models (#143, #182, #184)
  • ForceNet S2EF model (#150)
  • Torch implementation of ML relaxations (#92)
  • Support for on-the-fly graph construction (#92)
  • Pretrained model zoo (#144)
  • Jupyter notebooks to explore the OCP dataset (#90) and train an S2EF SchNet (#123)
  • Consolidated data preprocessing (#91, #152)

Other improvements

  • Trainer refactoring (#84, #135)
  • Support for running inference and relaxations from main.py (#92)
  • Support for saving predictions in EvalAI-compatible formats (#93)
  • Dataloader performance improvements (#154)
  • Bug fixes in metrics (#85, #75)
  • Bug fix in how angles are computed in DimeNet (#78)
  • Support for CircleCI (#98)
  • Sphinx documentation (#100)

- Python
Published by abhshkdz about 5 years ago

fairchem-core - 0.0.1

This is the initial release used to train all baseline models in the paper.

- Python
Published by abhshkdz over 5 years ago