Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Core50 benchmark with ICARL strategy #774

Closed
gab709 opened this issue Oct 15, 2021 · 6 comments · Fixed by #1463 · May be fixed by #1397
Closed

Core50 benchmark with ICARL strategy #774

gab709 opened this issue Oct 15, 2021 · 6 comments · Fixed by #1463 · May be fixed by #1397
Assignees
@lrzpellegrini
Labels
Benchmarks Related to the Benchmarks module bug Something isn't working good first issue Good for newcomers

Comments

@gab709
Copy link
Contributor

gab709 commented Oct 15, 2021

ICarl strategy returns an error with Core50 benchmark:
scenario = CORe50(scenario="nc", run=9)

The error is:
AttributeError: 'GenericCLScenario' object has no attribute 'n_classes_per_exp'

Other nc benchmarks belong to "NCScenario" class and this issue does not appear.
@AntonioCarta AntonioCarta added Benchmarks Related to the Benchmarks module bug Something isn't working labels Oct 18, 2021
@AntonioCarta
Copy link
Collaborator

As a quick fix, you can easily compute n_classes_per_exp yourself by using exp.dataset.targets.

@vlomonaco vlomonaco added the good first issue Good for newcomers label Nov 11, 2021
@ggraffieti
Copy link
Member

ggraffieti commented Nov 12, 2021 •
edited

Update: benchmarks created with the method create_multi_dataset_generic_benchmark have the same problem (no attribute n_classes_per_exp and classes_order).
I did not investigate much, but seems that also benchmarks created with create_generic_benchmark_from_filelists (as CORe50) have the same problem.

Maybe is related to the generic benchmarks?

@ashok-arjun
Copy link
Contributor

@ggraffieti I think it's related to how the structure of the generic benchmarks is.

I'd like to take up this issue. You can assign it to me.

How might I approach it? @AntonioCarta @ggraffieti

@lantao1234
Copy link

When i create a paths_benchmark, the function have the same problem.

AttributeError: 'GenericCLScenario' object has no attribute 'n_classes_per_exp'

@ema-marconato
Copy link

ema-marconato commented Jul 12, 2022 •
edited

Is still an open issue? I'm facing the same problem with ICarL implementation.

@Melika-Ayoughi
Copy link

I have the same problem with ego objects benchmark and icarl. Is it still not fixed?

@lrzpellegrini lrzpellegrini self-assigned this May 17, 2023
lrzpellegrini added a commit to lrzpellegrini/avalanche that referenced this issue May 30, 2023
@lrzpellegrini
Added regression tests for issue ContinualAI#774
eef6333
@lrzpellegrini lrzpellegrini mentioned this issue May 31, 2023
Open
lrzpellegrini added a commit to lrzpellegrini/avalanche that referenced this issue Jul 19, 2023
@lrzpellegrini
Fix issue ContinualAI#774
960d013
@lrzpellegrini lrzpellegrini mentioned this issue Jul 19, 2023
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@lrzpellegrini lrzpellegrini

Labels
Benchmarks Related to the Benchmarks module bug Something isn't working good first issue Good for newcomers
Projects
None yet
Milestone
No milestone
9 participants
@vlomonaco @AntonioCarta @ggraffieti @Melika-Ayoughi @lantao1234 @gab709 @lrzpellegrini @ashok-arjun @ema-marconato