You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thanks a lot for this awesome project! I am currently trying to reproduce the results from the sparsity experiment and I think I found some minor bugs:
In run_sparsity_experiments.py in line 277-289 (training the unregularized model) the refset must be enlarged to work with REF=100 samples.
--> change line 281 to: refset = torch.utils.data.TensorDataset(torch.cat([Xtrain_tensor]*REFS))
Additionally, ytest is not defined so one needs to add ytest = ytest_tensor.detach().cpu().numpy()
after line 280
In plot_results.ipynb you are plotting testscores, testsparsity, and testshaps but I think none of them is defined. Since I am not sure how those values are computed/obtained it would be great if you could help me out.
Thank you very much & Best,
Robin
The text was updated successfully, but these errors were encountered:
Hi,
Thanks a lot for this awesome project! I am currently trying to reproduce the results from the sparsity experiment and I think I found some minor bugs:
In
run_sparsity_experiments.py
inline 277-289
(training the unregularized model) therefset
must be enlarged to work withREF=100
samples.--> change line 281 to:
refset = torch.utils.data.TensorDataset(torch.cat([Xtrain_tensor]*REFS))
Additionally, ytest is not defined so one needs to add
ytest = ytest_tensor.detach().cpu().numpy()
after line 280
In
plot_results.ipynb
you are plottingtestscores
,testsparsity
, andtestshaps
but I think none of them is defined. Since I am not sure how those values are computed/obtained it would be great if you could help me out.Thank you very much & Best,
Robin
The text was updated successfully, but these errors were encountered: