Instructions to use logasja/auramask-ensemble-earlybird with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use logasja/auramask-ensemble-earlybird with Keras:
# !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://logasja/auramask-ensemble-earlybird") - Notebooks
- Google Colab
- Kaggle
Download assets/input.png from logasja/auramask-ensemble-earlybird: direct link, hf CLI and curl.
- Browser
- Download file 100 kB
-
https://huggingface.co/logasja/auramask-ensemble-earlybird/resolve/main/assets/input.png
- Command line
-
hf download hf://logasja/auramask-ensemble-earlybird/assets/input.png
-
curl -L -o input.png https://huggingface.co/logasja/auramask-ensemble-earlybird/resolve/main/assets/input.png
100 kB

- Xet hash:
- b78e25b0671b20a7c7ecb9062d347ddcfffc40f1ea6b66aa39c6282839dde8e8
- Size of remote file:
- 100 kB
- SHA256:
- 2724369cf7f553f35c3a9e29293d46e337a51a6f0220e2c1465aff1d2496bb20
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.