Instructions to use keras-io/PointNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TF-Keras
How to use keras-io/PointNet with TF-Keras:
# Note: 'keras<3.x' or 'tf_keras' must be installed (legacy) # See https://github.com/keras-team/tf-keras for more details. from huggingface_hub import from_pretrained_keras model = from_pretrained_keras("keras-io/PointNet") - Notebooks
- Google Colab
- Kaggle
Value error!
#2
by smdt - opened
ValueError: File format not supported: filepath=/Users/st/.cache/huggingface/hub/models--keras-io--PointNet/snapshots/...12abe18c. Keras 3 only supports V3 .keras files and legacy H5 format files (.h5 extension). Note that the legacy SavedModel format is not supported by load_model() in Keras 3. In order to reload a TensorFlow SavedModel as an inference-only layer in Keras 3, use keras.layers.TFSMLayer(/Users/st/.cache/huggingface/hub/models--keras-io--PointNet/snapshots/...12abe18c, call_endpoint='serving_default') (note that your call_endpoint might have a different name).