Closed tdzdog closed 1 year ago
@tdzdog I have the same issue. I am also aiming to split my dataset. Do you have the code for splitting the data? Thanks a lot!
The categories are not overlapping. Instances of Task 1 will be present only while training Task 1, and not in any future tasks. Instances of Task 2, will not be present while training on Task 1.
@tdzdog I have the same issue. I am also aiming to split my dataset. Do you have the code for splitting the data? Thanks a lot!
Have you solved this problem?
Can the code for splitting the data be provided? I am aiming to split our custom dataset. But there is still some confusion after reading the paper. To be specific, you split the whole data into four tasks. But are there categories overlapping among the tasks? For example, are instances of task-2 categories in task 1 during training? Or are there instances of task-1 categories in following tasks 2, 3, and 4?