updated todo
This commit is contained in:
parent
84dd1f093e
commit
3240150542
5
main.py
5
main.py
|
|
@ -7,14 +7,13 @@ from gfun.generalizedFunnelling import GeneralizedFunnelling
|
||||||
|
|
||||||
"""
|
"""
|
||||||
TODO:
|
TODO:
|
||||||
- [!] add support for Binary Datasets (e.g. cls) - NB: CLS dataset is loading only "books" domain data
|
- [!] CLS dataset is loading only "books" domain data
|
||||||
- [!] documents should be trimmed to the same length (?)
|
- [!] documents should be trimmed to the same length (?)
|
||||||
- [!] logging
|
- [!] overall gfun results logger
|
||||||
- add documentations sphinx
|
- add documentations sphinx
|
||||||
- [!] zero-shot setup
|
- [!] zero-shot setup
|
||||||
- FFNN posterior-probabilities' dependent
|
- FFNN posterior-probabilities' dependent
|
||||||
- re-init langs when loading VGFs?
|
- re-init langs when loading VGFs?
|
||||||
- [!] loss of Attention-aggregator seems to be uncorrelated with Macro-F1 on the validation set!
|
|
||||||
- [!] experiment with weight init of Attention-aggregator
|
- [!] experiment with weight init of Attention-aggregator
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue