In LRA/datasets/text.py the get_tc_datasets is called with max_length = 1000. In the code this is then concatenated with np.zeros(24), to get a length of 1024. But the maximum length for text classification is 4k, right? Do you just call the get_tc_datasets with max_length = 4000? Or is there another place in the code where you handle this?
Thanks! Best, Arne
Hello,
In
LRA/datasets/text.py
theget_tc_datasets
is called withmax_length = 1000
. In the code this is then concatenated withnp.zeros(24)
, to get a length of 1024. But the maximum length for text classification is 4k, right? Do you just call theget_tc_datasets
withmax_length = 4000
? Or is there another place in the code where you handle this? Thanks! Best, Arne