descriptron-core
Evidence-tiered species descriptions, keys and audits from phenomic matrices.
Pure pip: no torch, no CUDA, no compiler. Installs in about a minute on Linux, macOS and Windows. With the deposited COCO files it reproduces every analysis in the methods paper without a model of any kind — the audit, key, matrix, novelty scoring and delimitation are all deterministic.
pip install descriptron-core
descriptron --list # the 62 programs in this package
descriptron biorag_key_builder_v1 --help
biorag-audit --help
Writing treatments is the only step that calls a language model:
pip install "descriptron-core[llm]"
For mask prediction, landmark transfer and scale-bar reading, add
descriptron-vision; for the
annotation GUI, descriptron-gui.
The programs are shipped as data and executed with runpy, exactly as they run
from a shell, so packaging cannot quietly change what they do.
1 maintainer
Metadata
1 maintainer
Release files for descriptron-core 2.5.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| descriptron_core-2.5.1.tar.gz | 3.0 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| descriptron_core-2.5.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 6.2 MB
Release files / descriptron_core-2.5.1.tar.gz
| Download URL | descriptron_core-2.5.1.tar.gz |
|---|---|
| Size | 3.0 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ef3a810827792e3a22b6a3101a234d1a4912e1212d96f041047229239f7c4676
|
|
BLAKE2b-256 checksum How to use checksums |
8ebdc4a3c813643a292148ceb3217e7f3bc796a6e02d82116cb42f1e2a231afb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.4
|
Release files / descriptron_core-2.5.1-py3-none-any.whl
| Download URL | descriptron_core-2.5.1-py3-none-any.whl |
|---|---|
| Size | 3.2 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c002066c94ec400bf903fe825dfe0a420be055f7b1585ef2c7c30e1bb834728e
|
|
BLAKE2b-256 checksum How to use checksums |
82cf82320d40a5f359a66ca81d1c15bb344769d6972e3bc604949f2e34eb0e51
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.4
|
