ValueError: `class_weight` not supported for 3+ dimensional targets. with class_weight

[s1guma]

Hi,

I got an errorValueError: "class_weight" not supported for 3+ dimensional targets. with class_weight, when I run a baseline.py (with only text in emotion classification)with class_weight as below that is provided in README. I didn't make any changes to bc-LSTM model, but should I make a new loss function considering class_weight or something? Could you give me advice to be able to use class_weight without any problems? Thank you in advance.

using command: python baseline.py -classify emotion -modality text -train

fit parameter:

history = model.fit(self.train_x, self.train_y,
                            epochs=self.epochs,
                            batch_size=self.batch_size,
                            sample_weight=self.train_mask,
                            shuffle=True,
                            callbacks=[early_stopping, checkpoint],
                            validation_data=(
                                self.val_x, self.val_y, self.val_mask),
                            class_weight={0: 4.0, 1: 15.0, 2: 15.0,
                                          3: 3.0, 4: 1.0, 5: 6.0, 6: 3.0}
                            )