PRASHANT PANDEY
PRASHANT PANDEY
Hi @fcdl94 what is the CUDA version you used for your code?
> For the paper we used a A100, but we also tested on a Titan XP and a Tesla T4 and both work fine with smaller batch sizes. It is...
> One more hint for the those who are trying multiple GPU, you may change > > https://github.com/facebookresearch/audio2photoreal/blob/3a94699243ff66255398532f1705b0b31e0e1ae7/model/diffusion.py#L276 > > to > > ```python > cp = torch.load(cp_path, map_location='cpu') >...
Is dataset available? @Guhanxue
Sure. I will train the model from scratch. Waiting for the metric calculation script on test data for Hardi dataset. Thanks.
Hi @tiangexiang can you please clarify how one can get the results reported in the paper on test data after the training stage III is over?
Thank you. Waiting eagerly for the evaluation script. Also for the Sherbrooke dataset, is their a way to compute any quantitative metric on it as well? Can we use, https://dipy.org/documentation/1.1.0./examples_built/snr_in_cc/...
Hi @tiangexiang Can you please update the metric code. Thanks.
Thank you for prompt response @tiangexiang.
And which backbone/model is used?