-
Beta Was this translation helpful? Give feedback.
Answered by
Liu-lqq
Nov 16, 2022
Replies: 1 comment
-
Thank you for your attention. |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
su-sin-yu
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Thank you for your attention.
This is because we processed the data into a format that the model can directly use, when the sequence length is less than 200, we will pad -1 to it to make the length of all sequences equal 200.
If you want to get the original sequence, you can see the file "train_valid.csv", but this file can't be used directly by the models.
You can find the processed details in the file "pykt/preprocess/split_datasets.py"