Richard Brown

Results 68 comments of Richard Brown

Hm, I think for pytorch based applications, we always want the channel in front of spatial dimensions. Granted, matplotlib and opencv expect them at the end. I'll put this as...

@wyli Any idea why I'm seeing [this](https://github.com/Project-MONAI/MONAI/runs/7694587970?check_suite_focus=true#step:8:12033)? The import is nested in an `optional_import`.

Will wait to see if this passes CI, added .avi example video in case .mp4 codec missing. If both missing, skip. Also silence stderr error from OpenCV C++.

I can certainly see why this would be useful in your use case. But I think the name should be something more specific than `log_warning`; it's a specific kind of...

Honestly, I'm not entirely sure it belongs in any of our transforms. Perhaps we could have a checklist suggesting debugging steps for users, and this could be one of the...

Yes I certainly see your point that if we put it in a checklist, less people benefit from it than if we place it in our code. You're right, maybe...

Hi there, I have some datasets (video from file and video from video camera) in a [file on my repository](https://github.com/rijobro/real_time_seg/blob/main/python/video_seg.py). Feel free to tidy this up (e.g., the transforms need...

I have created a PR with the dataset but don't think it should be merged until a tutorial has been created that uses it. Can be based on my tutorial...

Thanks @doursand ! I can't see where `best_metric_model.pth` or the two `nii.gz` files are used. Are they used? If so, would it be possible to minimise the size of the...

Looks great, thanks for all the hard work. A few points: 1. There are a few classes here that already exist in a more general form in our code base....