Load saved models doesn't find MultiColumnEmbedding layer

[gladomat]

I tried loading a saved model but it can't load it and instead gives an error:

from tensorflow.keras.models import load_model mod_path = 'model_1.h5' load_model(mod_path)

The error:

ValueError: Unknown layer: MultiColumnEmbedding

[jackguagua]

There are two ways:

dt.save(filepath)
newdt = deeptable.DeepTable.load(filepath)
preds = newdt.predict(X_test)

from deeptables.models.layers import dt_custom_objects
from tensorflow.keras.models import load_model 

mod_path = 'model_1.h5' 
load_model(mod_path, dt_custom_objects)

[gladomat]

There's a bug in deeptable.py at line 660 where the model is saved. Please change os.makedirs to os.makedir.