David Kelley

I brainstormed a bit with Geoff, and one thing we caught was that you need to set -k 1 for the akita_data.py script to perform Gaussian smoothing of the data...

Hi, this indicates a mismatch between the sequence lengths, data resolution, and model pooling. If you send the statistics.json file of your dataset and you’re parameters json file of your...

Hi, I tracked down the bug. Pull the latest from master branch and rerun the notebook from the beginning, including the dataset generation.

Hi, can you share some details about how you're running the script and the error output that you see? I thought I fixed this bug.

I can't reproduce the error. Can you make sure you've pulled the latest code from master and cleared out all of the data so that you're starting from scratch?

Hmm that's puzzling. What version of Tensorflow are you using?

Hi Sara, can you say a little more about your goal? It'll influence how I can best help. It'd be a little tricky for me to track down the exact...

Hi, you can ignore the checkpoint message; that's for restarting training. The bigger issue is that Tensorflow doesn't seem to be installed properly. I'd start fresh.

Hi, which file are you referring to?

Those variants were all scored using the hg19 reference. I acquired the precise variants from here: https://storage.googleapis.com/broad-alkesgroup-public/LDSCORE/1000G_Phase3_plinkfiles.tgz