Sang-gil Lee

Sorry for the late reply. The >1 hour hang is indeed strange and shouldn't happen (the default stdout logging interval is 100 (`display_step`)). Could you test again with `display_step =...

Oops, sorry about the delayed issue post in this repo. Filed the report to the PyTorch repo about two weeks ago, so please stick to v0.4.1 until the issue is...

Update: the issue still persists in the [latest 1.0.1 release.](https://github.com/pytorch/pytorch/releases/tag/v1.0.1)

Note: `DistributedDataParallel` implementation from @1ytic circumvents the multi-GPU issue, so please use `train_apex.py` of the master branch until the issue from `DataParallel` (from `train.py`) is resolved.

Update: the issue was [fixed with the 1.2.0 release](https://github.com/pytorch/pytorch/pull/22983). We'll keep this issue open for a while for a future reference.

Maybe late to the discussion, but since I've PR'd the u-net fix ([#35](https://github.com/meetshah1995/pytorch-semseg/issues/21)), see issue [#21](https://github.com/meetshah1995/pytorch-semseg/issues/21)), Here's my comments. A strict U-net implementation does not use padding (Fig 1 in...

@irexyc Yes you're right. For the net to utilize the "valid" padding strategy of convolutions, you may want to tile the (388x388) image to have a shape of 572x572 like...

Hi! Sadly I have not tried to run the official Sonnet code myself, and just ported the core implementation of RMC with the Sonnet code just for the reference. So...

I've fired up the code and let it run forever and actually forgot about it for like 5 days. And checking it after seeing your issue, it was reaching 91%...

I've uploaded a bit overdue experimental results of the nth farthest task. Definitely takes way longer than the reported results from the paper. I will play with other hyperparameters when...