dluvizon/deephar

Cannot reproduce results in the NTU dataset

Closed this issue · 1 comments

Hi,
Great work and thanks for sharing the code!

I've downloaded the current code and can reproduce results using the 'eval_penn_ar_pe_merge' code. However, when I run the experiment on the NTU dataset ('eval_ntu_ar_merge_pe_merge') code, I often get wrong classifications (e.g., 2 out of 50 classifications are correct). Can you verify if one can reproduce the results with the given code for the NTU dataset?

Thanks,
duygu

It was a mistake on my side, I'm closing the issue.