DeepStack
DeepStack copied to clipboard
jcborges
DeepStack: Ensembling Keras Deep Learning Models into the next Performance Level
How do I implement a weighted average ensemble using models that takes 2 inputs. I pass these 2 inputs as a list to the train_batches and val_batches parameter of the...
# from keras.utils import to_categorical cannot import name 'to_categorical' from 'keras.utils'
/opt/conda/lib/python3.7/site-packages/deepstack/ensemble.py in 11 import glob 12 from deepstack.base import Member ---> 13 from keras.utils import to_categorical 14 15 ImportError: cannot import name 'to_categorical' from 'keras.utils' (/opt/conda/lib/python3.7/site-packages/keras/utils/__init__.py)
while running this line "from deepstack.ensemble import DirichletEnsemble" error is cannot import name 'to_categorical' from 'keras.utils' (/usr/local/lib/python3.7/dist-packages/keras/utils/__init__.py) if we use "from tensorflow.keras.utils import to_categorical" in place of "from keras.utils import...
As the title clearly describes the feature request I'm making, I think it'd be really beneficial to be able to use the the `validation_split` configuration during the `KerasMember` construction, just...
Great library!! How do you predict on unseen test data and ensemble using this deep stack?
Hello, I am afraid I didn't quite understand from the documentation clearly what should be passed as train_batches and val_batches... is it the the predictions made by the model that...
Hey, I tried to create a kerasMember using flow_from_dataframe option and I passed the data generators as arguments into KerasMember function. But, it is raising the value error. So, this...
I am trying to stack two trained keras models. The fit goes fine but there is an error in the describe, although the val data and the train data are...
