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.

Pre-labeling workflow

Send model predictions straight back to your labeling tool:

model.predict("images/", export="cvat")     # CVAT-for-images 1.1 XML pre-labels
model.predict("images/", export="coco")     # or COCO JSON
model.predict("huge_scans/", tiles="auto")  # tile very large images so small
                                            # objects stay detectable

Training quality features: a val split in data.yaml enables validation during training (best.pt tracks real validation fitness, per-class AP is logged, --patience N stops early); --class-balance oversamples images containing rare classes; auspex calibrate --weights best.pt --data data.yaml stores per-class confidence thresholds in the checkpoint so classes with different score scales all show up at their own best operating point.

Very small objects

If your objects are only a few pixels across at training resolution, the default detection grid (finest stride 8) cannot resolve them. Two options, in a train.yaml:

model:
  strides: [4, 8, 16, 32]   # adds a finer detection level
train:
  micro_batch: 2            # ~4x the anchors; halve the batch at 768 px
augment:
  native_crop_p: 0.5        # or: train on zoomed windows of large source images

Measured on a set where half the objects were smaller than one grid cell, the finer level roughly doubled F1 on the smallest classes. It is a trade, not a free win: long thin objects (road-like lines spanning much of the frame) tend to fragment into several detections, so leave it off for those. Both settings are off by default.

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.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for sohanurislamshuvo from gravatar.com sohanurislamshuvo

Credits

Author: Md. Sohanur Islam Shuvo

License

AUSPEX END-USER LICENSE AGREEMENT (EULA)

Requires

Python >=3.10

Report project as malware

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.

auspex_vision-0.4.0-cp313-cp313-win_amd64.whl (6.8 MB view details)

Uploaded CPython 3.13Windows x86-64

auspex_vision-0.4.0-cp313-cp313-win32.whl (6.6 MB view details)

Uploaded CPython 3.13Windows x86

auspex_vision-0.4.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (19.8 MB view details)

Uploaded CPython 3.13manylinux: glibc 2.17+ x86-64

auspex_vision-0.4.0-cp313-cp313-macosx_11_0_arm64.whl (7.1 MB view details)

Uploaded CPython 3.13macOS 11.0+ ARM64

auspex_vision-0.4.0-cp312-cp312-win_amd64.whl (6.9 MB view details)

Uploaded CPython 3.12Windows x86-64

auspex_vision-0.4.0-cp312-cp312-win32.whl (6.6 MB view details)

Uploaded CPython 3.12Windows x86

auspex_vision-0.4.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (20.2 MB view details)

Uploaded CPython 3.12manylinux: glibc 2.17+ x86-64

auspex_vision-0.4.0-cp312-cp312-macosx_11_0_arm64.whl (7.2 MB view details)

Uploaded CPython 3.12macOS 11.0+ ARM64

auspex_vision-0.4.0-cp311-cp311-win_amd64.whl (6.9 MB view details)

Uploaded CPython 3.11Windows x86-64

auspex_vision-0.4.0-cp311-cp311-win32.whl (6.7 MB view details)

Uploaded CPython 3.11Windows x86

auspex_vision-0.4.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (19.6 MB view details)

Uploaded CPython 3.11manylinux: glibc 2.17+ x86-64

auspex_vision-0.4.0-cp311-cp311-macosx_11_0_arm64.whl (7.2 MB view details)

Uploaded CPython 3.11macOS 11.0+ ARM64

auspex_vision-0.4.0-cp310-cp310-win_amd64.whl (6.9 MB view details)

Uploaded CPython 3.10Windows x86-64

auspex_vision-0.4.0-cp310-cp310-win32.whl (6.7 MB view details)

Uploaded CPython 3.10Windows x86

auspex_vision-0.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.8 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.17+ x86-64

auspex_vision-0.4.0-cp310-cp310-macosx_11_0_arm64.whl (7.2 MB view details)

Uploaded CPython 3.10macOS 11.0+ ARM64

File details

Details for the file auspex_vision-0.4.0-cp313-cp313-win_amd64.whl.

File metadata

File hashes

Hashes for auspex_vision-0.4.0-cp313-cp313-win_amd64.whl
Algorithm Hash digest
SHA256 54c61ce3aefc7501822182f3987798ac422ac033a1a839a3ddd58504703c8677
MD5 7307f710f18d0a72db3dbed4642061b6
BLAKE2b-256 f7bfb1776f4832860004bba9f8bdf46372b9de8c9cf5d3ce091d93df6823160e

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp313-cp313-win32.whl.

File metadata

  • Download URL: auspex_vision-0.4.0-cp313-cp313-win32.whl
  • Upload date:
  • Size: 6.6 MB
  • Tags: CPython 3.13, Windows x86
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for auspex_vision-0.4.0-cp313-cp313-win32.whl
Algorithm Hash digest
SHA256 f762cd5863a4e005c2435a3b554e32fe2c3a6b3b6fa7cba73a3dac4c687be090
MD5 75b887cfa83237257df18c21ae4da6dd
BLAKE2b-256 9c4f1e9e722803b0662cd39e9df743dd1f690b68ab90478a38ec86e750e33477

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for auspex_vision-0.4.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 dcc315ee26d0f8ee0bf9a10a27813a262c895261077970c96d6e59f77efa5d9e
MD5 357251afaa8b83e653bf7879700649e4
BLAKE2b-256 c2b272e638f29c454a348e4f95179d62549794d4320631f5cae2b368ccaf43e2

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp313-cp313-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for auspex_vision-0.4.0-cp313-cp313-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 c3898cdbbf7efd76574b8530529e4e6fe843c1340e2850071c2f9be4925807fc
MD5 c04efc54782463452d2e2193b9420d0e
BLAKE2b-256 0feee8f86f277a5d6c6f5ca3c39d6b656a93a76e55d59f0a7ce0ad98f5792330

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp312-cp312-win_amd64.whl.

File metadata

File hashes

Hashes for auspex_vision-0.4.0-cp312-cp312-win_amd64.whl
Algorithm Hash digest
SHA256 243e040465cf208084a7346de68b46cb566b531af5e948038e8d06032a18faf3
MD5 8b38d17636f4818d9299c84e2f705174
BLAKE2b-256 af6535124aface6c4a1f434ea38acabc02d4c9a8dd88c4c9b4d98a6435caaca0

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp312-cp312-win32.whl.

File metadata

  • Download URL: auspex_vision-0.4.0-cp312-cp312-win32.whl
  • Upload date:
  • Size: 6.6 MB
  • Tags: CPython 3.12, Windows x86
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for auspex_vision-0.4.0-cp312-cp312-win32.whl
Algorithm Hash digest
SHA256 b7602b7e330597f78dfe4413d89fc8e8ebc5dd59ddfa9594880a27e79e592c02
MD5 ec89df3db28bffc71bb588cadd191d9f
BLAKE2b-256 33ef4fbd3b56fe72d70920306add441c3e84809ecec2f4b791d701dd4a0d52b6

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for auspex_vision-0.4.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 480993e9b857714d31dd0a151b37399099aafc48c8236f31c8f11ffc3e716cf7
MD5 e2c28bebb9a9045a9d8786ce9404a3b1
BLAKE2b-256 e261b28cd3dc58b78b12f45121d25548053237e98890bac0b098b9101641bcbc

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp312-cp312-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for auspex_vision-0.4.0-cp312-cp312-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 2379f71d05e55145636a66fa318459cbf8c52d26635a0ce7dd6eb6479267824f
MD5 2df4b2c22f66299a56f20958d69afac8
BLAKE2b-256 146d3fb49f443be82c832a874198fbd172165f14498c196007756e4706486902

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp311-cp311-win_amd64.whl.

File metadata

File hashes

Hashes for auspex_vision-0.4.0-cp311-cp311-win_amd64.whl
Algorithm Hash digest
SHA256 b960c9b2554024b69c7612fbc162140841b1980202dd9d1ce772c473982e5a7c
MD5 9e6a9a4613477b32b4395f1d599bf52c
BLAKE2b-256 a7e33e90ed1e72417f20a294716c3a75a69911dd66d0084ac050cba7a4369926

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp311-cp311-win32.whl.

File metadata

  • Download URL: auspex_vision-0.4.0-cp311-cp311-win32.whl
  • Upload date:
  • Size: 6.7 MB
  • Tags: CPython 3.11, Windows x86
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for auspex_vision-0.4.0-cp311-cp311-win32.whl
Algorithm Hash digest
SHA256 12267ee6101cbfd8bff112d11c84c5af557b4253884da3305e55bc6902ca17cc
MD5 4c9609ea46e803b3e36e30346facbd39
BLAKE2b-256 930fe80c4275e7b67e1bc7c6809866e2c89c20a568dc8e81148abbf1f8969a5c

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for auspex_vision-0.4.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 4d089a39718d869461a1441bf745a60a157cdb479ea07493c576d35cfe5447bb
MD5 84cada6fa926cfc1e0c5f5150ac63556
BLAKE2b-256 e224349c824860d8f1c58e5a8d9dac9193c407bc0e7c7d8394c8505ab02f775d

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp311-cp311-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for auspex_vision-0.4.0-cp311-cp311-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 d07a54948e967318115147c500e90a7308822523cc033621143fe8b7a46b8cd8
MD5 a1f97605a32c3cbb62415a24c825262e
BLAKE2b-256 6ded9128904c5f2606e38e471e793e3148b6754d859f51bca3bb5f9848aacb1d

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp310-cp310-win_amd64.whl.

File metadata

File hashes

Hashes for auspex_vision-0.4.0-cp310-cp310-win_amd64.whl
Algorithm Hash digest
SHA256 149606782afd606d7795bfdb5356486d1b4022761a3b6b32123d5e5439571774
MD5 dbc2936a5e6fc2d748b9af44f54f58eb
BLAKE2b-256 91cb64e41ccf653bd5c2af0f6c2d331b3eefeddb74bf3040f9d55b16fd79ef49

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp310-cp310-win32.whl.

File metadata

  • Download URL: auspex_vision-0.4.0-cp310-cp310-win32.whl
  • Upload date:
  • Size: 6.7 MB
  • Tags: CPython 3.10, Windows x86
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for auspex_vision-0.4.0-cp310-cp310-win32.whl
Algorithm Hash digest
SHA256 19afbff30cb98b1158c2cda441fe8d6ab2b3436963ca1885e648cfa6358e75e9
MD5 e0dde741bccf908cf1eda77df3e2c842
BLAKE2b-256 01602ae9c691c036b66060f27160e42bcbecf0614fc747d3ee08e291e820d8cb

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for auspex_vision-0.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 e9df957b3fe9b299426e443448a6a0a42b396685f335708a690768d84f17485d
MD5 d227eec9644fab6c6251f9d2d36c997f
BLAKE2b-256 940cb79cb98f02e96b968883a7dfcb47eefcd932374e8af9b1c2b81b71260704

See more details on using hashes here.

File details

Details for the file auspex_vision-0.4.0-cp310-cp310-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for auspex_vision-0.4.0-cp310-cp310-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 ff1783fa1a9004c85369b1a25e32cf8e20ca3ed76f6caf5fb187d45c7561ee39
MD5 f46b2f58164e3f9167f8c5f43c7c141d
BLAKE2b-256 b65ec51b3caebdb3a3047f1fc830c21d28b6ee4926090278970e422e17c28f14

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page