ValueError: Supported target types are: ('binary', 'multiclass'). Got 'unknown' instead.

[aminzadenoori]

Hi,
when I want to run "train.py --v lstm" I have this error, ValueError: Supported target types are: ('binary', 'multiclass'). Got 'unknown' instead.
can you guide me on how to fix it?
thank you.

[aminzadenoori]

I solved that by:

from sklearn.preprocessing import LabelEncoder

label_encoder = LabelEncoder()
y = label_encoder.fit_transform(target_labels)

[mahmoudaghvami]

I found the same error.
the line 38 of train.py raise the error
line 38 for train, test in kfold.split(X, Y)
The error ValueError: Supported target types are: ('binary', 'multiclass'). Got 'unknown'

apprently Y is unknown

the fix by [aminzadenoori] does not work for me.
How to fix it?
@danielelic @aminzadenoori

[zendra123]

Hi @mahmoudaghvami I have the same error, have you found any solution, how to fix this?

[xiaoluobie]

I had the same problem:ValueError: Supported target types are: (‘binary‘, ‘multiclass‘). Got ‘unknown‘ instead.”, and now it's over.

You can try adding a code： y = y.ype (float) in front of this line of code：for fold_num, (train_index, test_index) in enumerate(skf.split(X, y)):

See my blog for detailed solutions and reasons.The CSDN address link is：
CSDN

I hope this is helpful
@mahmoudaghvami @zendra123

[zendra123]

@xiaoluobie thank you.