FACIL

FACIL copied to clipboard

Update: GDumb + minor fixes

3

Added GDumb and some minor fixes

mmasana

The meaning of model_old is confusing. In task 1, the number of heads of model_old is sometimes 1 and sometimes 2 during def eval.

1

Dear author, Thanks for your work. **Question 1:** I am quite confused about your definition of the model_old. **I thought model_old should be the model from the last tasks, therefore,...

XuMengyaAmy

gridsearch-tasks == -1 in args does not perform grid search

2

Hello! Thank you very much for this library - it's great! I have a question: The default value of `--gridsearch-tasks` in `main_incremental.py` is `-1`. And it has been given that...

ashok-arjun

Hi, this is not really an issue. I'm currently developing a classification model which is trained by event-driven samples. The number of labels/classes grows as new events are produced and...

AndreGuerra123

I have an error in the file exemplars_selection it says no samples to choose from for class 240, how to fix this?

1

nevasini

GridSearch to find the accurate lambda value

1

How to perform the grid search to find the accurate lambda value in ICARL approach for a custom dataset? Now the grid search is performed only on the learning rate...

arnabphoenix

LwM - no gradient in attention distillation loss

5

Hi, when experimenting with LwM in FACIL I noticed that the method behaves the same regardless of the choice of `gamma` parameter that controls attention distillation loss. Upon closer investigation,...

fszatkowski

Upperbound results

6

Hello! I have a confusion about how to view Upperbound(Joint) results. First of all, I am running the code by setting the approach to "joint" to see the Upperbound(Joint) result...

jmin0530

LwF CIFAR-100 (10/10) No exemplars accuracy

1

Hello, I noticed that the accuracy of the LwF method in CIFAR-100 (10/10) drops to 16% after 10 tasks when the No exemplars approach is used, which is different fromthe...

Yuki-Hong

accuracy

1

Does the accuracy of each stage only use the category validation set of the current task? Should the accuracy of all stages of training be taken as the final result?...

tb626