Matthew Muckley

No it's not expected. The images on the leaderboard are basically just a concatenation of your reconstruction with the target, so it looks like your reconstruction is several orders of...

Resolved comments unrelated to issue title. If continued problems arise, please create a new issue.

Hello @Can-Zhao it is not resolved, mostly because I'm working on several other projects and don't have time to fix it. I apologize for the inconvenience. Using an S3 bucket...

Hello @ZhengguoTan, the `if` statement covers if it's a test or challenge split *and* `test_path` is not none. So even if that check fails, the split could still be `"val"`,...

Closing due to inactivity and should have been fixed by 37ffc89309c941f00ac873f5dd9b6f537411cb10.

Hello @834799106, thanks for putting an issue here. Based on your error I doubt the `SliceDataset` class is the issue. For one, your program is not being terminated due to...

Hello @soumickmj, I ran your script on the knee validation data with [memory-profiler](https://pypi.org/project/memory-profiler/) and memory usage peaked pretty early a little bit less than 5 GB (see attached), staying flat...

Hello @soumickmj, I copied the wrong code. The paste I showed was with the dataloader, not the dataset. This is what I get with dataset. You can see the max...

One thing I notice is that you are both using Python 3.9. I could try Python 3.9 and check with that perhaps. EDIT: Sorry, I see you also tried Python...

Okay, I tested on Python 3.9 and I'm still getting the same behavior with `batch_size=4`. To help a bit more with this I'm including my complete `conda` environments that I...