etzinis / sudo_rm_rf

Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-Resolution Features which enables a more efficient way of separating sources from mixtures.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

'SuDORMRF' object has no attribute 'n_least_samples_req' Error

RyderZ-Neo opened this issue · comments

Hello etzinis . I am a fan of your work. I ran into object has no attribute 'n_least_samples_req' error when tried to run how_to_use notebook in master branch.
rec_sources_wavs = anechoic_separation_model(input_mix.unsqueeze(1)). Everything works fine before that line of code. Please help me if you can . @etzinis

Hello there! Thanks for your kind words! I fixed the issue which was caused by a previous fix that broke things, please try to use the newer way (shown in README and in the notebook) on how to load the pre-trained models.

Thank you for your answer.