For Tensorflow feature columns contain boolean value 0 and 1.
Should I be using tf.feature_column.numeric_column
or tf.feature_column.categorical_column_with_vocabulary_list?
You can use sequence_categorical_column_with_identity :
tf.feature_column.sequence_categorical_column_with_identity('YOUR_FEATURE',2)
the second parameter is the number of buckets. If you have n consecutive integers [0,1,2 .. ,n-1] in your feature, you then write :
tf.feature_column.sequence_categorical_column_with_identity('YOUR_FEATURE',n)
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With