yluo42 / TAC

transform-average-concatenate (TAC) method for end-to-end microphone permutation and number invariant ad-hoc beamforming.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

how to generate the pkl?

shanhaidexiamo opened this issue · comments

Hi, I find the data generation part needs to read the pkl file , but if I want to modify the room size and num of mics, how to generate pkl? Does this mean that I need to manually modify the pkl file you provided?

I guess that the pkl files are generated with random parameters using a python script. Do not manually modify the pkl files. Write codes to generate them.

I guess that the pkl files are generated with random parameters using a python script. Do not manually modify the pkl files. Write codes to generate them.

yes. I think so. the code is incomplete, hope author can open more code

You should not modify the .pkl config files in order to correctly generate the dataset. data/create_dataset.py should be a complete file for generating the data.

If you want to create your own data (for data augmentation or other purposes), you can take a look at the items in the configurations and randomly generate more. Also take a look at data/create_dataset.py to see how the config files are used, e.g. the items in the .pkl files.