Unanswered
Hi There :)
Can Anybody Tell Me What The Best Practice Is For Performing A Normalization In The Preprocess.Py Script Used By Clearml-Serving? Currently I Use A Sklearn Minmaxscaler Which Is Loaded And Applied Before And After The Data Is Send To The Model
And as far as I can see there is no mechanism installed to load other objects than the model file inside the Preprocess class, right?
Well actually this is possible, let's assume you have another Model that is part of the preprocessing, then you could have:
something like that should work
def preprocess(...)
if not getattr(self, "_preprocess_model):
self._preprocess_model = joblib.load(Model(model_id).get_weights())
171 Views
0
Answers
one year ago
one year ago