How can save K-means estimator model?

General Discussion
,
#1

I develop a model with tf.compat.v1.estimator.experimental.KMeans for convert tf.lite version.(Because I will use this model on a mobile app).

When I want to save this model, it asks me for a function like below;

export_saved_model(
    export_dir_base,
    serving_input_receiver_fn,
    assets_extra=None,
    as_text=False,
    checkpoint_path=None,
    experimental_mode=ModeKeys.PREDICT
)

I don’t understand this func: serving_input_receiver_fn, can you please help

GitHub : AIforGraduationProject/Untitled.ipynb at main · kadirdundar/AIforGraduationProject · GitHub
documentation: tf.compat.v1.estimator.experimental.KMeans  |  TensorFlow v2.11.0

#3

Hey,
To save your model in dump is used where ‘wb’ means write binary . To load the saved model wherever need load is used where ‘rb’ means read binary. Here model is kmeans and filename is any local file, so use accordingly.