Instructions to use keras-io/Object-Detection-RetinaNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TF-Keras
How to use keras-io/Object-Detection-RetinaNet 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/Object-Detection-RetinaNet") - Notebooks
- Google Colab
- Kaggle
Issue Loading Model
Hello,
How was the model saved, or how to load the model? I have tried both tf.keras.models.load_model() and tf.saved_model.load(). Both times, I get the same error "OSError: Cannot parse file b'Object-Detection-RetinaNet/saved_model.pb': Error parsing message with type 'tensorflow.SavedModel'"
I know that the model is being found, because if I intentionally put the wrong path, I get the error message "SavedModel file does not exist at Object-detection-RetinaNet//{saved_model.pbtxt|saved_model.pb}"
cc @merve
Hello,
I had the same error.
This error is link to git LFS, when I openned my files i saw they were incorrect.
version https://git-lfs.github.com/spec/v1
oid sha256:b63e9e21122e676d34a09d795c6548c5fc6a75baf43c007b2a22629c177d1d6c
size 414583
When i re download the project with LFS active the error disapear
I hope this will help you