Downloads · 30 days
83
89% of all-time downloads
Addax-Data-Science/SOCAL-IRC-v3-6
SOCAL-IRC-v3-6 is a machine learning model from Addax-Data-Science. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for keras.
This repository contains open-source models redistributed for easy integration with AddaxAI, hosted by Addax Data Science. Each model retains its original license (see license files) and attribution. We comply with al…
Downloads · 30 days
83
89% of all-time downloads
All-time downloads
93
Public
Repo size
83.9 MB
Likes
0
Public
Click a slice to open those files.
.keras83.9 MB · 100%
From the Hugging Face model README
This repository contains open-source models redistributed for easy integration with AddaxAI, hosted by Addax Data Science. Each model retains its original license (see license files) and attribution. We comply with all original license terms. Users must review and comply with individual model licenses before use. See below for detailed model information including original sources, licenses, and attributions.
<strong>Developer</strong>
Irvine Ranch Conservancy (IRC), Orange County, California
<strong>Links</strong>
<ul> <li><a href="https://github.com/Monitoring-Research-IRC/irc-species-classification-model">Learn more</a></li> <li><a href="https://creativecommons.org/licenses/by-nc/4.0/">License (CC BY-NC 4.0)</a></li> <li><a href="https://github.com/Monitoring-Research-IRC/irc-species-classification-model#citation">Citation</a></li> </ul><strong>Model</strong>
IRC Species Classification Model v3.6, trained with the <a href="https://github.com/zaandahl/mewc">MEWC</a> framework. EfficientNetV2 Small at 384x384, Keras 3.3.3, 18 classes. The weights file <code>IRC.Species.Classification.Model.keras</code> is the unmodified asset of GitHub release v3.6.1 (sha256 <code>9ca887db2dac4067a532465e6cc18e71320639123c2a3d2d8bb42ce8ba1af6af</code>). Held-out test set of 3,669 images: overall accuracy 96.9%, macro F1 0.966 (numbers from the developer's README).
<strong>Files</strong>
<ul> <li><code>inference.py</code>: AddaxAI ModelInference implementation (TensorFlow backend).</li> <li><code>class_list.yaml</code>: the developer's class map, unmodified. Its values are the training-table order written by mewc-train, not the model's output indices; the model outputs follow the class names in alphabetical order (scikit-learn LabelEncoder), which is how <code>inference.py</code> and mewc-predict read them. Class names are emitted lowercase.</li> <li><code>taxonomy.csv</code>: class to taxonomy mapping for the AddaxAI filter tree, resolved against GBIF.</li> <li><code>LICENSE</code>: CC BY-NC 4.0, as published by the developer.</li> </ul>