Variable size serving input
For some reason mlflow serve
does not accept the variable sized input of the BruteForce
layer.
Things tested so far:
- Setting input spec
- Calling predict before
log_model
with various different sizes - Wrapping
BruteForce
by input layer (functional API) with specificinput_shape
. See https://gitlab.sauerburger.com/frank/movie-recommender/-/blob/80b23288e95f3fa65a1122db54ef1164a46547f5/movies.py#L327
The situation might change when switching from BruteForce
to ScaNN
layers.