search

tuanchien / asd

Active Speaker Detection
Apache License 2.0
19 stars 4 forks source link

Error while extracting mfcc features #7

Closed godatta closed 3 years ago

godatta commented 3 years ago

The audio.wav file is being stored inside each folder extracting the videos.

Screen Shot 2021-06-03 at 6 45 02 PM
tuanchien commented 3 years ago

Can you paste the code, commands, and configuration you are trying to run and use?

The output looks very odd. For example, it is thinking the pickle file 'test_annotations.pkl' is the name of a directory.

godatta commented 3 years ago

Thanks, I fixed this error. It was due to some directory mismatch in the config file.

However, I am running into this error (please see attached), whenever I try to evaluate your model (execute the evaluate.py file). Can you please let me know your CudaDNN and coda version since I suspect it might be a version issue. Or do you have any suggestions as to how can I fix this error?

Configuration of my machine is

NVIDIA-SMI 450.119.03 Driver Version: 450.119.03 CUDA Version: 11.0 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |===============================+======================+======================| | 0 Tesla V100-SXM2... On | 00000000:00:1E.0 Off | 0 | | N/A 31C P0 24W / 300W | 0MiB / 16160MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+

Screen Shot 2021-06-05 at 2 59 55 AM
tuanchien commented 3 years ago

cuda 10.2 worked for me.