Auspex

One model for every annotation type used in computer-vision labeling work: bounding boxes, instance polygons, keypoints, polylines, and image-level tags — trained on your own data with a few lines of code.

Supported annotation formats: COCO JSON, CVAT-for-images 1.1 XML, Pascal VOC XML — mixed freely in one training run.

Install

pip install auspex-vision        # import name: auspex

Wheels for Linux x86_64, Windows, and macOS Apple Silicon, Python 3.10–3.13. An NVIDIA GPU is recommended for training (precision is picked automatically for your hardware); CPU works for inference.

Use

from auspex import Auspex

model = Auspex(labelspace="labelspace.yaml")
model.train(data="data.yaml", epochs=150)          # train on your own data
results = model.predict("images/", save=True)      # detect

model = Auspex(weights="best.pt")                  # checkpoints are self-contained
model.val(data="data.yaml")

Or the console command: auspex train --data data.yaml --labelspace labelspace.yaml, auspex predict --weights best.pt --source images/, auspex val --weights best.pt --data data.yaml.

Data configuration

labelspace.yaml — your categories (order = class id), keypoint names + flip_pairs for skeleton classes, is_polyline: true for polyline classes, and image-level tags.

data.yaml — one entry per annotation source:

sources:
  - name: batch1
    path: annotations/batch1.xml   # CVAT 1.1 XML | COCO .json | VOC xml dir
    images_root: images/
    split: train
    provides: {rect: true, polygon: true, keypoint: false, polyline: false, tag: false}

provides declares which tasks a source actually labels — unlabeled tasks contribute nothing to training, so sources with different annotation coverage mix safely.

Growing a model over time: --transfer <checkpoint> continues from existing weights even when classes were added or reordered; --source-balance rebalances very unequal sources; --cache-records keeps memory flat on large datasets.

License

Proprietary software under an End-User License Agreement: licensed users may install and run Auspex and train models on their own data (the resulting weights are theirs); copying, redistribution, modification, and reverse engineering are prohibited. Contact the author for licensing inquiries.

Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

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

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

auspex_vision-0.2.3-cp313-cp313-win_amd64.whl (5.7 MB view details)

Uploaded Aug 4, 2026 CPython 3.13Windows x86-64

auspex_vision-0.2.3-cp313-cp313-win32.whl (5.5 MB view details)

Uploaded Aug 4, 2026 CPython 3.13Windows x86

auspex_vision-0.2.3-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (16.0 MB view details)

Uploaded Aug 4, 2026 CPython 3.13manylinux: glibc 2.17+ x86-64

auspex_vision-0.2.3-cp313-cp313-macosx_11_0_arm64.whl (5.9 MB view details)

Uploaded Aug 4, 2026 CPython 3.13macOS 11.0+ ARM64

auspex_vision-0.2.3-cp312-cp312-win_amd64.whl (5.7 MB view details)

Uploaded Aug 4, 2026 CPython 3.12Windows x86-64

auspex_vision-0.2.3-cp312-cp312-win32.whl (5.5 MB view details)

Uploaded Aug 4, 2026 CPython 3.12Windows x86

auspex_vision-0.2.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (16.4 MB view details)

Uploaded Aug 4, 2026 CPython 3.12manylinux: glibc 2.17+ x86-64

auspex_vision-0.2.3-cp312-cp312-macosx_11_0_arm64.whl (6.0 MB view details)

Uploaded Aug 4, 2026 CPython 3.12macOS 11.0+ ARM64

auspex_vision-0.2.3-cp311-cp311-win_amd64.whl (5.8 MB view details)

Uploaded Aug 4, 2026 CPython 3.11Windows x86-64

auspex_vision-0.2.3-cp311-cp311-win32.whl (5.6 MB view details)

Uploaded Aug 4, 2026 CPython 3.11Windows x86

auspex_vision-0.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (16.0 MB view details)

Uploaded Aug 4, 2026 CPython 3.11manylinux: glibc 2.17+ x86-64

auspex_vision-0.2.3-cp311-cp311-macosx_11_0_arm64.whl (6.0 MB view details)

Uploaded Aug 4, 2026 CPython 3.11macOS 11.0+ ARM64

auspex_vision-0.2.3-cp310-cp310-win_amd64.whl (5.8 MB view details)

Uploaded Aug 4, 2026 CPython 3.10Windows x86-64

auspex_vision-0.2.3-cp310-cp310-win32.whl (5.6 MB view details)

Uploaded Aug 4, 2026 CPython 3.10Windows x86

auspex_vision-0.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (15.3 MB view details)

Uploaded Aug 4, 2026 CPython 3.10manylinux: glibc 2.17+ x86-64

auspex_vision-0.2.3-cp310-cp310-macosx_11_0_arm64.whl (6.0 MB view details)

Uploaded Aug 4, 2026 CPython 3.10macOS 11.0+ ARM64

File details

Details for the file auspex_vision-0.2.3-cp313-cp313-win_amd64.whl.

File metadata

Download URL: auspex_vision-0.2.3-cp313-cp313-win_amd64.whl
Upload date: Aug 4, 2026
Size: 5.7 MB
Tags: CPython 3.13, Windows x86-64
Uploaded using Trusted Publishing? No
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for auspex_vision-0.2.3-cp313-cp313-win_amd64.whl
Algorithm	Hash digest
SHA256	`f37e476c2aa7f14bf28f5a8f69cfc55d9fba31500dd90b26da85b6dbbcb50023`
MD5	`6b2edb9abbe43839a492bae993a3ca3e`
BLAKE2b-256	`59f6fbfd3c8a14d4d94360093d1f62322752f8d3c7125dd2cdc5954ad0cbf9e4`

Algorithm	Hash digest
SHA256	`c5ec6521d43e3f0c306d1b9af8dc6ea0ae15ea03021120612c4d9930abb36445`
MD5	`05f9fd674da47a0abec528cb61f5a7dd`
BLAKE2b-256	`cda34c1bd2cfca3da2ac4c21c3b6dda594d0898f17bd50f2d77efee167911d1f`

Algorithm	Hash digest
SHA256	`5a999413b949c0aa57f990a3e7b38a5af515cb2f01ef871e3f357bf071d2b803`
MD5	`98992503eab429dd6eafa55cde6e04f1`
BLAKE2b-256	`bedbb6a5a19619c54fb18c61b4aaddb578ee954d37b30780ce57932ee7a3df78`

Algorithm	Hash digest
SHA256	`2cbecf39f094d33aac8448e942728a97a3c0d178ca27b6f63269f7f6a6ad36cc`
MD5	`bfc206fb8364a73055a1028c7b434594`
BLAKE2b-256	`ac8ce96a127c7867d7304593b20347cbcb33e35fdc2aebf5ef628a57c7b73857`

Algorithm	Hash digest
SHA256	`f103af50f9c808fe272db7bf204b95bf6013d270afa3165ff71c00f55bb92b31`
MD5	`5432ea5663e6e972c62ecca27c32ddee`
BLAKE2b-256	`f3b5fb0dfd41d51ce98d3083cdce50fd93650d7114d8270861de893a90864020`

Algorithm	Hash digest
SHA256	`18a93e00d026a7f582f2ba023fcf8a5e3f544fc4833957c1b4493deee022dcfd`
MD5	`821815bf146380ea23f3e44088a6e12d`
BLAKE2b-256	`eb8a6dfa1bbd31a890808dc7244b0dd6344f2ff7f98d81b295f9c4304704c512`

Algorithm	Hash digest
SHA256	`4c8cc0b71ba6631c5177abd9849c66b85d93d4ac2b2a2e2d550789b8f2abfaaf`
MD5	`d8e7ebc4c6de50ce459e8c99e3df2ca4`
BLAKE2b-256	`a30e5d8b75eebee2e78baa0067e96ff0bbeee1a41d036ed6685441d837e2046c`

Algorithm	Hash digest
SHA256	`c318c3f00ccad59297fdcc56a92f0f68c6c119ef82ebb9f21c5d939f515039bb`
MD5	`2546251f74d643a5783d5e3c3a06228f`
BLAKE2b-256	`1c002cf7c553f5b6c969657057b1582790cf62d98d4e2d58f760837d53390552`

Algorithm	Hash digest
SHA256	`79cc12aa2fa7b6784e7931ad0d26b24c300104fe47440540b5ecb553973dba1d`
MD5	`6647d0a2ed655c3e46b789b0c81e8691`
BLAKE2b-256	`689c76cbab2bbe97b4a2fdbe1b266cb9c090bc500a19071e7c800937dec2a174`

Algorithm	Hash digest
SHA256	`b598a68619cac8bf1fe4ef50287665f9c4b79198dc7415f00910d477bf1c5179`
MD5	`3a4eeec013026e9b42eb94e808d4b596`
BLAKE2b-256	`f248ebd578551663eb6c154bc5f19f09eeac83f89bbfc5f066f8d0e1cb268579`

Algorithm	Hash digest
SHA256	`1d5b6fc0e11f661d22cc29824e8f668e2b0517886742b3936748bcc13e9edd68`
MD5	`c12be59a3155dbeed175a8d90dc263c8`
BLAKE2b-256	`349166782bfb8a6a99469a58440b6a523169ece4c38e93e53ae14f5b1c67e8f8`

Algorithm	Hash digest
SHA256	`815834c2911b8d6a1da55d2273635c12facf18a6556a07a6c3c64caedff564e5`
MD5	`2e518d089edc4086fd0111acff996db3`
BLAKE2b-256	`adf9fd9642a2aadb2c42b28bda52fefc1da1ad434f1284b5f1b0a571354cf876`

Algorithm	Hash digest
SHA256	`bca5e3abf185c91715ba835ab9dd9400e7835ed34dcc7c84cbce93de00afcace`
MD5	`4dd93b4a70325d5f032f05ad88711f94`
BLAKE2b-256	`dd990c9ec097741fadbb53c9350ea8bcda5046a5e67483fdebe0608263d6245c`

Algorithm	Hash digest
SHA256	`e6aee5cf20ea7fde824defe72f33be79e73c1093f37df0cceb1bb98451d0f874`
MD5	`8362e4ffc385180664c7d9b74edaa639`
BLAKE2b-256	`98d18156ad2af573862874f9ad902072402fee24e84246bce4d309a9a27e2879`

Algorithm	Hash digest
SHA256	`5057eb89cbbec526abc249c9782b27be03075446d8ca25939ba214e468a7274c`
MD5	`bf7d927204d905f80c97d096fcddb960`
BLAKE2b-256	`464047377a91aab2dbf8a9bae5cf6fc7071c4153995e94e231bad72a325cd993`

Algorithm	Hash digest
SHA256	`95d1690fb71b5b8341108c787f58195059b4586f4699fd9e6c3fd8d1a302b7a4`
MD5	`f5771c08ab19e70398fffc717f51e972`
BLAKE2b-256	`f592aa67769cd7b82cb93100d7d79c54370d05d774d9898213e13852efc24ae8`

auspex-vision 0.2.3

Auspex

Install

Use

Data configuration

License

Key dates

1 maintainer

Credits

License

Requires

Download files

Source Distributions

Built Distributions

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

Release history Release notifications | RSS feed