Avantika Lal
Avantika Lal
Possibly relevant cuML issue: https://github.com/rapidsai/cuml/issues/2478
@teju85 thanks for the reminder, we'll check and get back to you.
@teju85 We checked this and the problem still exists, despite the cuML bug being resolved. @cjnolet is looking into it.
This issue should be resolved now: https://github.com/rapidsai/cuml/issues/3645 Will test and close.
Hi @albertdyu , sorry for the broken link. Tutorial 1 is here: https://github.com/clara-parabricks/AtacWorks/blob/dev-v0.4.0/tutorials/tutorial1.ipynb
Hi Yichao, The model that we were describing in our paper takes 50 kb intervals as input and returns 50 kb intervals as output. However, the receptive field of the...
Hi Yichao, yes, that calculation is correct for a single layer! However, the total receptive field of the entire model is higher since there are multiple convolutional layers stacked on...
HI @elffairy90. --weights_path should be not a bigwig file but the path to a trained AtacWorks model. You can either train a model yourself using clean and noisy bigwig files...
Hi @umasstr , for the best results we recommend training your own model, if you have matched low/high quality data available. The noisy data and clean data could have any...
Great to see the custom model working well overall, though I agree the low-level background is a problem. The model shouldn't require a nonzero output at every coordinate. Could you...