Instructions to use TheVortexProject/insectnet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use TheVortexProject/insectnet with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("TheVortexProject/insectnet", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
Align historical baseline with living Perch 2 deployment
Browse files
README.md
CHANGED
|
@@ -17,15 +17,20 @@ datasets:
|
|
| 17 |
|
| 18 |
InsectNet v0.1.0 is a preserved research classifier for scoring insect- and amphibian-related acoustic classes from frozen BirdNET v2.4 output logits.
|
| 19 |
|
| 20 |
-
This
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
-
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## Release identity
|
| 25 |
|
| 26 |
```text
|
| 27 |
Release: insectnet-v0.1.0
|
| 28 |
-
Artifact: classifier.joblib
|
| 29 |
SHA-256: 5e6ecfc68d78a2cf2e9e9e47da5cb58d696e8de354fd620cfcccc5db9da48702
|
| 30 |
Bytes: 474,892
|
| 31 |
Status: historical research reference
|
|
@@ -72,10 +77,9 @@ The model file does not embed thresholds, a version number, or its original trai
|
|
| 72 |
- device addresses or credentials;
|
| 73 |
- exact collection locations;
|
| 74 |
- raw or private field audio;
|
| 75 |
-
- later experimental model candidates;
|
| 76 |
- claims of production readiness.
|
| 77 |
|
| 78 |
-
The original live sidecar diverged from
|
| 79 |
|
| 80 |
## Verify the preserved artifact
|
| 81 |
|
|
@@ -112,6 +116,34 @@ The command returns one probability per declared class. These scores are model a
|
|
| 112 |
- The classifier relies on BirdNET logits and cannot score raw audio by itself.
|
| 113 |
- There is no validated automated-decision threshold policy in this release.
|
| 114 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 115 |
## Provenance
|
| 116 |
|
| 117 |
The surviving records identify these source families:
|
|
@@ -121,11 +153,11 @@ The surviving records identify these source families:
|
|
| 121 |
- **iNaturalist audio:** licenses vary per recording; the original per-record manifest is unavailable.
|
| 122 |
- **Private field negatives:** not redistributed.
|
| 123 |
|
| 124 |
-
See [`PROVENANCE.md`](PROVENANCE.md) and the release manifest for the exact surviving claims and gaps.
|
| 125 |
|
| 126 |
## Privacy and security
|
| 127 |
|
| 128 |
-
The public release intentionally omits exact collection location, network topology, account names, credentials, private paths, and raw evidence. See [`SECURITY_AND_PRIVACY.md`](SECURITY_AND_PRIVACY.md).
|
| 129 |
|
| 130 |
## License
|
| 131 |
|
|
|
|
| 17 |
|
| 18 |
InsectNet v0.1.0 is a preserved research classifier for scoring insect- and amphibian-related acoustic classes from frozen BirdNET v2.4 output logits.
|
| 19 |
|
| 20 |
+
This repository preserves one canonical v0.1 release identity and also carries separately
|
| 21 |
+
versioned Perch 2 research candidates. It does **not** publish live sensor addresses,
|
| 22 |
+
deployment credentials, exact collection locations, private media, or an unattended
|
| 23 |
+
capture service.
|
| 24 |
|
| 25 |
+
Public discovery and versioned downloads are organized in the
|
| 26 |
+
[The Vortex Project — Multi-Taxa Bioacoustics](https://huggingface.co/collections/TheVortexProject/the-vortex-project-multi-taxa-bioacoustics-6a6d92a9e0938f507e931388)
|
| 27 |
+
Hugging Face collection. GitHub remains the source, tests, and release-engineering surface.
|
| 28 |
|
| 29 |
## Release identity
|
| 30 |
|
| 31 |
```text
|
| 32 |
Release: insectnet-v0.1.0
|
| 33 |
+
Artifact: src/insectnet/data/classifier.joblib
|
| 34 |
SHA-256: 5e6ecfc68d78a2cf2e9e9e47da5cb58d696e8de354fd620cfcccc5db9da48702
|
| 35 |
Bytes: 474,892
|
| 36 |
Status: historical research reference
|
|
|
|
| 77 |
- device addresses or credentials;
|
| 78 |
- exact collection locations;
|
| 79 |
- raw or private field audio;
|
|
|
|
| 80 |
- claims of production readiness.
|
| 81 |
|
| 82 |
+
The original v0.1 live sidecar diverged from this public source during early field experiments and is not a current deployment target. It has been superseded operationally by the separately versioned Perch 2 specialist architecture; the preserved v0.1 artifact remains a historical BirdNET-logit reference.
|
| 83 |
|
| 84 |
## Verify the preserved artifact
|
| 85 |
|
|
|
|
| 116 |
- The classifier relies on BirdNET logits and cannot score raw audio by itself.
|
| 117 |
- There is no validated automated-decision threshold policy in this release.
|
| 118 |
|
| 119 |
+
## Perch 2 research artifacts and field heads
|
| 120 |
+
|
| 121 |
+
Three provenance-locked specialist lines were trained and audited in July 2026. None
|
| 122 |
+
replaces the preserved BirdNET-logit v0.1 artifact. Each line has an explicit public
|
| 123 |
+
research boundary and a separate operational status. FrogNet's public mirror contains
|
| 124 |
+
the exact checked JSON/NPZ bundle used by its private review-only field head; the public
|
| 125 |
+
InsectNet and ChickenNet research artifacts must not be conflated with later private
|
| 126 |
+
field bundles.
|
| 127 |
+
|
| 128 |
+
| Candidate | Status | Key external result |
|
| 129 |
+
|---|---|---|
|
| 130 |
+
| [ChickenNet Research 0.1.0](models/chickennet-research-0.1.0-perch2/MODEL_CARD.md) | frozen public joblib not deployed; later private JSON/NPZ successor operates as a review-only field head | 33/42 broad-head hits on a locked iNaturalist chicken challenge; 10/1,308 candidate activations on a private local confound set |
|
| 131 |
+
| [InsectNet Research 0.2.0](models/insectnet-research-0.2.0-perch2/MODEL_CARD.md) | frozen public joblib not deployed; later private JSON/NPZ successor operates as a review-only field head | 11/26 broad activations on an untouched iNaturalist dog challenge |
|
| 132 |
+
| [FrogNet Research 0.1.0](models/frognet-research-0.1.0-perch2/MODEL_CARD.md) | public noncommercial research artifact; exact strict bundle deployed privately for review | 1,253/1,308 local frog-window activations and 0/3,781 tested confound activations at threshold `0.95` |
|
| 133 |
+
|
| 134 |
+
All three lines consume 1,536-dimensional Google Perch 2 embeddings from five-second,
|
| 135 |
+
32 kHz mono windows. They include exact model/data hashes, grouped split reports,
|
| 136 |
+
hierarchy contracts, source summaries, and challenge reports. They do not include Perch
|
| 137 |
+
weights or source audio.
|
| 138 |
+
|
| 139 |
+
## Training strategy
|
| 140 |
+
|
| 141 |
+
[`docs/PERCH2_TRAINING_STRATEGY.md`](docs/PERCH2_TRAINING_STRATEGY.md) records the
|
| 142 |
+
provenance-first design used for the Perch 2 specialist heads. The current FrogNet
|
| 143 |
+
research and operational contract is frozen in [`docs/FROGNET_FIELD_PROBE.md`](docs/FROGNET_FIELD_PROBE.md).
|
| 144 |
+
The dated architecture and artifact-versus-runtime boundary for all three living heads is
|
| 145 |
+
recorded in [`docs/LIVING_DEPLOYMENT.md`](docs/LIVING_DEPLOYMENT.md).
|
| 146 |
+
|
| 147 |
## Provenance
|
| 148 |
|
| 149 |
The surviving records identify these source families:
|
|
|
|
| 153 |
- **iNaturalist audio:** licenses vary per recording; the original per-record manifest is unavailable.
|
| 154 |
- **Private field negatives:** not redistributed.
|
| 155 |
|
| 156 |
+
See [`docs/PROVENANCE.md`](docs/PROVENANCE.md) and the release manifest for the exact surviving claims and gaps.
|
| 157 |
|
| 158 |
## Privacy and security
|
| 159 |
|
| 160 |
+
The public release intentionally omits exact collection location, network topology, account names, credentials, private paths, and raw evidence. See [`docs/SECURITY_AND_PRIVACY.md`](docs/SECURITY_AND_PRIVACY.md).
|
| 161 |
|
| 162 |
## License
|
| 163 |
|