Getting Out-of-memory (OOM) error on running the model on GPU. about speech-denoising-wavenet HOT 5 CLOSED

Got the trick to solve this error. Actually the model size gets too big for the limited GPU memory to accommodate the model with the default parameters in the config.json file. To reduce the model size, you just need to tweak one parameter that is "dilations" in "model" dictionary from default value of 9 to something small like 4 or 5. The config.json file to modify is the one present in the parent directory itself and NOT the one in sessions/001/config.json.
Mind you that the given pretrained model won't work after changing 'dilations' value for inference. So you will have to first train a new model using the training dataset given and then do the inference. @wuweijia1994

from speech-denoising-wavenet.

I also meet this problem of ResourceExhaustedError. My setup is Tesla K80 GPU.

from speech-denoising-wavenet.

Thank you so much for the reply. Now the problem is solved. Now I know how good the GPU this guy has for "9 dilations".

from speech-denoising-wavenet.

DillipKS is correct, feel free to re-train a smaller model. Note that the GPU we used for our work was a Titan X Pascal (12GB-VRAM).

from speech-denoising-wavenet.

@jordipons I am unable to perform inference on the machine with Nvidia Tesla T4 16gb, I am getting out of memory error

from speech-denoising-wavenet.