This model intends to support conservation in the Congo Basin (specifically Cameroon). CBNet is short for CongoBasinNet. It currently covers 12 species. The model was trained on about 15,000 images (source: WWF Cameroon). Accuracy is 0.902 and macro accuracy is 0.817 on a held-out test set of about 2,200 images, though performance varies by class. This model is a fine-tuned version of SpeciesNet.
The model can be used freely in AddaxAI.
- Downloads last month
- 46
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://alexvmt/CBNet")