Ryan Stout

Thanks so much for the info. Currently I load up each image, then write out tiles to disk and then read those tiles in during the stacking. (Similar to what...

@pedrocr unfortunately, the disk read/write time adds up. (since they get paged out of ram) I'm not sure if its any easier, but what we really need is just something...

@pedrocr Just wanted to follow up. Really we just need to be able to decode the image from start to finish in some sort of chunks, so we don't load...

@LebedevRI thanks for the info. I would need .nef, .cr2, and .awr support ideally. For me it's really about being able to load only tiles of the image at a...

I'm seeing a similar issue when running with nn.DataParallel: ``` RuntimeError: Caught RuntimeError in replica 0 on device 0. Original Traceback (most recent call last): File "/home/ryanstout/.local/share/virtualenvs/arsenal_train2-TlJZ47AR/lib/python3.7/site-packages/torch/nn/parallel/parallel_apply.py", line 60, in...

There is a helper for doing tags, but not archives. Let me know if archives is what you want. If not you can make a layout with a tag list...

Ok, how do you envision archives? I would probably just do another helper tag so people can easily customize the layout.

@saurabhvyas yea, any luck figuring it out? Thanks!

@lessw2020 Great project, thanks for all of the hard work on it! I'm seeing similar issues. Interestingly, when switching to multiple gpu's (even multiplying the LR by the number of...

I'm seeing the same issue running adams2019 on my code. If you can't narrow it down, I've got a fairly simple pipeline that triggers it if I set the wrong...