I am training a simple sequential model for NLP in keras. Here is the model architecture:

from keras.models import Sequential
from keras import layers
from keras.layers import Embedding, Flatten, Dense

embedding_dim = 500

model = Sequential()

model.add(layers.Embedding(input_dim = vocab_size, 
                           output_dim = embedding_dim, input_shape = (2,)))
model.add(layers.Flatten())
model.add(layers.Dense(10, activation = 'relu'))
model.add(layers.Dense(1, activation = 'softmax'))
model.compile(optimizer = 'adam',
              loss = 'categorical_crossentropy',
              metrics = METRICS)

I also implemented early stopping and class weights as follows:

early_stopping = tf.keras.callbacks.EarlyStopping(
    monitor = 'val_loss', 
    verbose = 1,
    patience = 10,
    mode = 'max',
    restore_best_weights = True)

class_weight = {1: 3.,
                2: 2.,
                3: 1.5,
                4: 1.,
                5: 3.,
                6: 3.
                }

I then called model.fit() as follows:

history = model.fit(X_train, y_train,
                    epochs = 100,
                    verbose = 2,
                    validation_data = (X_val, y_val),
                    batch_size = 10,
                    class_weight = class_weight,
                    callbacks = [early_stopping]
                   )

This resulted in this error:

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
Cell In[74], line 9
      1 class_weight = {1: 3.,
      2                 2: 2.,
      3                 3: 1.5,
   (...)
      6                 6: 3.
      7                 }
----> 9 history = model.fit(X_train, y_train,
     10                     epochs = 100,
     11                     verbose = 2,
     12                     validation_data = (X_val, y_val),
     13                     batch_size = 10,
     14                     class_weight = class_weight,
     15                     callbacks = [early_stopping]
     16                    )

File ~AppDataLocalanaconda3Libsite-packageskerassrcutilstraceback_utils.py:122, in filter_traceback.<locals>.error_handler(*args, **kwargs)
    119     filtered_tb = _process_traceback_frames(e.__traceback__)
    120     # To get the full stack trace, call:
    121     # `keras.config.disable_traceback_filtering()`
--> 122     raise e.with_traceback(filtered_tb) from None
    123 finally:
    124     del filtered_tb

File ~AppDataLocalanaconda3Libsite-packagespandascoreseries.py:1040, in Series.__getitem__(self, key)
   1037     return self._values[key]
   1039 elif key_is_scalar:
-> 1040     return self._get_value(key)
   1042 # Convert generator to list before going through hashable part
   1043 # (We will iterate through the generator there to check for slices)
   1044 if is_iterator(key):

File ~AppDataLocalanaconda3Libsite-packagespandascoreseries.py:1156, in Series._get_value(self, label, takeable)
   1153     return self._values[label]
   1155 # Similar to Index.get_value, but we do not fall back to positional
-> 1156 loc = self.index.get_loc(label)
   1158 if is_integer(loc):
   1159     return self._values[loc]

File ~AppDataLocalanaconda3Libsite-packagespandascoreindexesbase.py:3798, in Index.get_loc(self, key)
   3793     if isinstance(casted_key, slice) or (
   3794         isinstance(casted_key, abc.Iterable)
   3795         and any(isinstance(x, slice) for x in casted_key)
   3796     ):
   3797         raise InvalidIndexError(key)
-> 3798     raise KeyError(key) from err
   3799 except TypeError:
   3800     # If we have a listlike key, _check_indexing_error will raise
   3801     #  InvalidIndexError. Otherwise we fall through and re-raise
   3802     #  the TypeError.
   3803     self._check_indexing_error(key)

KeyError: 0

As per a similar question regarding this error in Keras, “KeyError: 0” when trying to load a sequential model in Keras, I tried updating my version of Keras. Howeve, this didn’t change anything. I believe the error is something internal to Keras, but I’m not sure what’s wrong.

Please advise!