Skip to main content
NepTrainKit logo
PyPI downloads Python version Codecov License

English | 简体中文

NepTrainKit

NepTrainKit is a desktop application for preparing, auditing, and visualizing training datasets for neuroevolution potentials (NEPs). It complements, rather than replaces, long-running GPUMD training or DFT calculations. Its focus is the repetitive work around those calculations: generating candidate structures, cleaning problematic samples, selecting representative configurations, and passing a well-prepared dataset back into the DFT and GPUMD workflow.

What you can do

  • Make Dataset: generate strained, perturbed, defective, surface, doped, magnetic, and solvated candidate structures with composable cards.
  • NEP Dataset Display: inspect structures, errors, and distributions; remove problematic samples; and export a clean subset.
  • Representative selection: reduce a candidate pool to a smaller, more representative set with methods such as farthest point sampling (FPS).
  • Training-result inspection: load NEP- and DeepMD-related outputs, locate high-error structures, and identify data gaps for the next iteration.
  • Project tracking: use Data Management to record models, dataset paths, and notes across multiple iterations.

Installation

We recommend installing NepTrainKit in a dedicated Python environment. Python 3.10 through 3.13 is supported.

conda create -n nepkit python=3.10
conda activate nepkit
pip install NepTrainKit

After installation, launch the application with either command:

nepkit
# or
NepTrainKit

NEP compute backend

NepTrainKit does not compile the NEP compute backend into the application. pip installs the separate nep-adapters dependency:

Platform Installed backend
macOS / Windows CPU
Linux x86_64 CPU and CUDA in one wheel

The Linux CUDA path requires a compatible NVIDIA driver, but installing the wheel does not require a local CUDA toolkit or NVCC. Source builds and supported CUDA architectures are documented in the NEPAdapters repository.

After launching NepTrainKit, select Auto, CPU, or CUDA under Settings → NEP Backend. Auto uses CUDA when the installed wheel, driver, and model support it; otherwise NepTrainKit explains why it is continuing on CPU. Explicit CUDA requests fail instead of silently changing backend.

Settings → NEP Settings → NEP runtime updates can install a compatible nep-adapters update without replacing NepTrainKit. NepTrainKit also checks this runtime in the background whenever the app opens; no-update and network-failure cases stay silent, while an available update opens an installation prompt. Pip installations store the managed wheel under the user configuration directory; the Windows standalone build stores it under runtime/nep-adapters/versions beside NepTrainKit.exe. A wheel is activated only after SHA256 verification and a fresh-process health check, and takes effect after restart.

Confirm the installed runtime with:

python -c "import nep_adapters as n; print(n.backend_status('cpu')); print(n.backend_status('cuda'))"

Windows package

If you prefer not to compile NepTrainKit locally, download NepTrainKit.windows-x86_64.zip from GitHub Releases. This package requires 64-bit Windows on x86_64 hardware.

Documentation and support

If this is your first time using NepTrainKit, begin with Quickstart and Cleaning candidate structures before DFT in the user documentation. If you already know which class of configurations you need, go directly to the Make Dataset card reference.

Citation

If NepTrainKit contributes to your research, please cite:

@article{CHEN2025109859,
title = {NepTrain and NepTrainKit: Automated active learning and visualization toolkit for neuroevolution potentials},
journal = {Computer Physics Communications},
volume = {317},
pages = {109859},
year = {2025},
issn = {0010-4655},
doi = {https://doi.org/10.1016/j.cpc.2025.109859},
url = {https://www.sciencedirect.com/science/article/pii/S0010465525003613},
author = {Chengbing Chen and Yutong Li and Rui Zhao and Zhoulin Liu and Zheyong Fan and Gang Tang and Zhiyong Wang},
}

License and third-party code

NepTrainKit is licensed under the GNU General Public License v3.0 or later. See LICENSE for details.

NEP computation is provided by the separate nep-adapters dependency. NepTrainKit no longer vendors the NEP_CPU or GPUMD backend source trees.

See THIRD_PARTY_NOTICES.md for the remaining attribution in this repository. The nep-adapters distribution carries its own backend source notices and licenses.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

neptrainkit-3.0.1.tar.gz (6.8 MB view details)

Uploaded Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

neptrainkit-3.0.1-cp313-cp313-win_amd64.whl (7.7 MB view details)

Uploaded CPython 3.13Windows x86-64

neptrainkit-3.0.1-cp313-cp313-macosx_15_0_x86_64.whl (7.7 MB view details)

Uploaded CPython 3.13macOS 15.0+ x86-64

neptrainkit-3.0.1-cp313-cp313-macosx_15_0_arm64.whl (7.6 MB view details)

Uploaded CPython 3.13macOS 15.0+ ARM64

neptrainkit-3.0.1-cp312-cp312-win_amd64.whl (7.7 MB view details)

Uploaded CPython 3.12Windows x86-64

neptrainkit-3.0.1-cp312-cp312-macosx_15_0_x86_64.whl (7.7 MB view details)

Uploaded CPython 3.12macOS 15.0+ x86-64

neptrainkit-3.0.1-cp312-cp312-macosx_15_0_arm64.whl (7.6 MB view details)

Uploaded CPython 3.12macOS 15.0+ ARM64

neptrainkit-3.0.1-cp311-cp311-win_amd64.whl (7.7 MB view details)

Uploaded CPython 3.11Windows x86-64

neptrainkit-3.0.1-cp311-cp311-macosx_15_0_x86_64.whl (7.7 MB view details)

Uploaded CPython 3.11macOS 15.0+ x86-64

neptrainkit-3.0.1-cp311-cp311-macosx_15_0_arm64.whl (7.6 MB view details)

Uploaded CPython 3.11macOS 15.0+ ARM64

neptrainkit-3.0.1-cp310-cp310-win_amd64.whl (7.7 MB view details)

Uploaded CPython 3.10Windows x86-64

neptrainkit-3.0.1-cp310-cp310-macosx_15_0_x86_64.whl (7.7 MB view details)

Uploaded CPython 3.10macOS 15.0+ x86-64

neptrainkit-3.0.1-cp310-cp310-macosx_15_0_arm64.whl (7.6 MB view details)

Uploaded CPython 3.10macOS 15.0+ ARM64

File details

Details for the file neptrainkit-3.0.1.tar.gz.

File metadata

  • Download URL: neptrainkit-3.0.1.tar.gz
  • Upload date:
  • Size: 6.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for neptrainkit-3.0.1.tar.gz
Algorithm Hash digest
SHA256 1900a07fa314e3c67e1bd24df7f6c2d6bbbaebfe1c2c0927eda33169e3388c0d
MD5 357f35871af01380eafce14377971166
BLAKE2b-256 2b3b00b5161e432e0913d27d36d694cee4dffd6b5b53cc160c1d1fb6d37ddb37

See more details on using hashes here.

Provenance

The following attestation bundles were made for neptrainkit-3.0.1.tar.gz:

Publisher: python-publish.yml on aboys-cb/NepTrainKit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file neptrainkit-3.0.1-cp313-cp313-win_amd64.whl.

File metadata

File hashes

Hashes for neptrainkit-3.0.1-cp313-cp313-win_amd64.whl
Algorithm Hash digest
SHA256 11dc8e9fe4fbf6ccb6a75d497afc65e493c369a928c5c7e853d8591526a554ff
MD5 62b5b1d5bd820cb5840a0d97dcf78c2f
BLAKE2b-256 2c5d014c73c04faaf8e2fa73e1f47af53ad30804411cc7e1d458932ff0b3f816

See more details on using hashes here.

Provenance

The following attestation bundles were made for neptrainkit-3.0.1-cp313-cp313-win_amd64.whl:

Publisher: python-publish.yml on aboys-cb/NepTrainKit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file neptrainkit-3.0.1-cp313-cp313-macosx_15_0_x86_64.whl.

File metadata

File hashes

Hashes for neptrainkit-3.0.1-cp313-cp313-macosx_15_0_x86_64.whl
Algorithm Hash digest
SHA256 2da80dc2bafe8e5518b11754039434ea872a6b15b548516f047312dca6e636a0
MD5 df6a0a86dd094c86be58dab631fc2032
BLAKE2b-256 92870d8b66b413a8c34841bf7e4fb710b81bd75ad6e20414e5844b65bc2cc939

See more details on using hashes here.

Provenance

The following attestation bundles were made for neptrainkit-3.0.1-cp313-cp313-macosx_15_0_x86_64.whl:

Publisher: python-publish.yml on aboys-cb/NepTrainKit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file neptrainkit-3.0.1-cp313-cp313-macosx_15_0_arm64.whl.

File metadata

File hashes

Hashes for neptrainkit-3.0.1-cp313-cp313-macosx_15_0_arm64.whl
Algorithm Hash digest
SHA256 d1e4c78e880fe57e067fd818ab6d71ae688455d9c225ffaad2a772d9824a89a4
MD5 7492b5252a928d46b6e900c56dda7cfe
BLAKE2b-256 252879347dac692ff6e502ef76a1ae05db3841aaecabcd937b95e12c592f3037

See more details on using hashes here.

Provenance

The following attestation bundles were made for neptrainkit-3.0.1-cp313-cp313-macosx_15_0_arm64.whl:

Publisher: python-publish.yml on aboys-cb/NepTrainKit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file neptrainkit-3.0.1-cp312-cp312-win_amd64.whl.

File metadata

File hashes

Hashes for neptrainkit-3.0.1-cp312-cp312-win_amd64.whl
Algorithm Hash digest
SHA256 8403fffb442a85ad7e70ac992a27a07fb3ddec0a4534b93e5b7bcb939a05c19c
MD5 80c712c9cc8ef1925ce867ca6c1787cb
BLAKE2b-256 16a3de33bef7eb94342c3be369ba39fb9ff96245af0ccdb8af62a05425a42ac1

See more details on using hashes here.

Provenance

The following attestation bundles were made for neptrainkit-3.0.1-cp312-cp312-win_amd64.whl:

Publisher: python-publish.yml on aboys-cb/NepTrainKit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file neptrainkit-3.0.1-cp312-cp312-macosx_15_0_x86_64.whl.

File metadata

File hashes

Hashes for neptrainkit-3.0.1-cp312-cp312-macosx_15_0_x86_64.whl
Algorithm Hash digest
SHA256 91f1582235a275894979e9b2efd388c0493940dd21525a93eb7b07c1621be0fb
MD5 811ab6b402e8c8c16fda0ca14d3a9087
BLAKE2b-256 f1328c7d5d92002f46306f75d15cf52221893f545a07e4d4289eea176ee562eb

See more details on using hashes here.

Provenance

The following attestation bundles were made for neptrainkit-3.0.1-cp312-cp312-macosx_15_0_x86_64.whl:

Publisher: python-publish.yml on aboys-cb/NepTrainKit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file neptrainkit-3.0.1-cp312-cp312-macosx_15_0_arm64.whl.

File metadata

File hashes

Hashes for neptrainkit-3.0.1-cp312-cp312-macosx_15_0_arm64.whl
Algorithm Hash digest
SHA256 b0240ccfd68bc44d7d606c4c11641e7f79880fdf32eab5d63339a6375e27944d
MD5 efa36c1cd82b4c7eb4c9e8f88bdcb36c
BLAKE2b-256 0e146e8695637899cdcd6ee1eb82eb59c5ba6ea6fe563f3568178ad8f417c5fa

See more details on using hashes here.

Provenance

The following attestation bundles were made for neptrainkit-3.0.1-cp312-cp312-macosx_15_0_arm64.whl:

Publisher: python-publish.yml on aboys-cb/NepTrainKit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file neptrainkit-3.0.1-cp311-cp311-win_amd64.whl.

File metadata

File hashes

Hashes for neptrainkit-3.0.1-cp311-cp311-win_amd64.whl
Algorithm Hash digest
SHA256 ec47f396e38a3325eb0fe361e2cc2a7d5d5b36ae5915bf66a6d0f939b3b7c64e
MD5 3b5f376625a018d197c2d8eec4495030
BLAKE2b-256 d902b067d16a2a092305784f26b4386318e52f8034ec84da01f1beb3be4d61a8

See more details on using hashes here.

Provenance

The following attestation bundles were made for neptrainkit-3.0.1-cp311-cp311-win_amd64.whl:

Publisher: python-publish.yml on aboys-cb/NepTrainKit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file neptrainkit-3.0.1-cp311-cp311-macosx_15_0_x86_64.whl.

File metadata

File hashes

Hashes for neptrainkit-3.0.1-cp311-cp311-macosx_15_0_x86_64.whl
Algorithm Hash digest
SHA256 9e664a5f1662f0b62dd17bf761e5c57fe71401b6bb4c739970eff14d9d86ceed
MD5 10812effafb31f9882afd8f078f001c6
BLAKE2b-256 01fdc058be91a26dd84298a5fdb1abef8cc58c8b0fd8c0f04f24f9ba59bc5c46

See more details on using hashes here.

Provenance

The following attestation bundles were made for neptrainkit-3.0.1-cp311-cp311-macosx_15_0_x86_64.whl:

Publisher: python-publish.yml on aboys-cb/NepTrainKit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file neptrainkit-3.0.1-cp311-cp311-macosx_15_0_arm64.whl.

File metadata

File hashes

Hashes for neptrainkit-3.0.1-cp311-cp311-macosx_15_0_arm64.whl
Algorithm Hash digest
SHA256 f12d3add3b747d8910a958b001650065d231673531e632157131cc7a30783ed4
MD5 870f33500e2d74abb493b47bd0c7d4d8
BLAKE2b-256 4b2b4629129e60ccfa60f91332ad63cb170a30b281b9926078b64b993bbf63ef

See more details on using hashes here.

Provenance

The following attestation bundles were made for neptrainkit-3.0.1-cp311-cp311-macosx_15_0_arm64.whl:

Publisher: python-publish.yml on aboys-cb/NepTrainKit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file neptrainkit-3.0.1-cp310-cp310-win_amd64.whl.

File metadata

File hashes

Hashes for neptrainkit-3.0.1-cp310-cp310-win_amd64.whl
Algorithm Hash digest
SHA256 e8083e16233c763975f5d81383611af9243221a8ead1a02cda517c0cc9ef7bf5
MD5 78e2e59c4db0f2dd8f4b824cb2e1c536
BLAKE2b-256 ac619df8a350e66b7f6cc7ad0c7b409a475f219940a8a245374e5e9659d223a2

See more details on using hashes here.

Provenance

The following attestation bundles were made for neptrainkit-3.0.1-cp310-cp310-win_amd64.whl:

Publisher: python-publish.yml on aboys-cb/NepTrainKit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file neptrainkit-3.0.1-cp310-cp310-macosx_15_0_x86_64.whl.

File metadata

File hashes

Hashes for neptrainkit-3.0.1-cp310-cp310-macosx_15_0_x86_64.whl
Algorithm Hash digest
SHA256 f399f39c3a26fceb118ff3c00276725254be92c2dfdcaefad90ce40f63416d14
MD5 be4dbb7a478f49e961e19b8fabf4ee87
BLAKE2b-256 059a7f8a9a15f3f9e28f3e5448d4d24c59175f026352a5cd52c80c3ce0bcc631

See more details on using hashes here.

Provenance

The following attestation bundles were made for neptrainkit-3.0.1-cp310-cp310-macosx_15_0_x86_64.whl:

Publisher: python-publish.yml on aboys-cb/NepTrainKit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file neptrainkit-3.0.1-cp310-cp310-macosx_15_0_arm64.whl.

File metadata

File hashes

Hashes for neptrainkit-3.0.1-cp310-cp310-macosx_15_0_arm64.whl
Algorithm Hash digest
SHA256 f7a1bf76b1d5b82885147faba1ebefc2b80c9d9a6a4e687c9997f310e3deae99
MD5 2023e96c403e5c846af86c292bb66800
BLAKE2b-256 14ce69a6596e626fb9cca3b862e68015c569638e0062f032b8aab05bd3ffbe89

See more details on using hashes here.

Provenance

The following attestation bundles were made for neptrainkit-3.0.1-cp310-cp310-macosx_15_0_arm64.whl:

Publisher: python-publish.yml on aboys-cb/NepTrainKit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

3.0.1 This release

13 files

3.0.0

17 files

2.8.4

17 files

2.8.3

17 files

2.8.1

17 files

2.8.0

17 files

2.7.2

17 files

2.7.1

17 files

2.7.0

17 files

2.6.8

17 files

2.6.7

17 files

2.6.6

17 files

2.6.5

17 files

2.6.4

17 files

2.6.3

17 files

2.6.2

17 files

2.6.1

17 files

2.5.4

19 files

2.5.3

19 files

2.5.1

19 files

2.5.0

19 files

2.4.2

19 files

2.4.1

19 files

2.4.0

19 files

2.3.1

19 files

2.3.0

19 files

2.2.1

19 files

2.2.0

19 files

2.1.0

19 files

2.0.6

19 files

2.0.5

19 files

2.0.4

1 file

2.0.3

1 file

2.0.0

1 file

1.7.1

1 file

1.7.0

1 file

1.5.9

1 file

1.5.8

1 file

1.5.7

1 file

1.5.6

1 file

1.5.5

1 file

1.5.4

1 file

1.5.3

1 file

1.5.2

1 file

1.5.1

1 file

1.5.0

1 file

1.4.9

1 file

1.4.8

1 file

1.4.7

1 file

1.4.6

1 file

1.4.5

1 file

1.4.4

1 file

1.4.3

1 file

1.4.2

1 file

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page