Tuan Truong
Tuan Truong
From what I read in the article, nnUNet starts with a median patch size at the target spacing then slowly reduces the patch size to meet the GPU requirements as...
@SkafteNicki Thank you for your quick response. Please find bellow the methods for forward, training steps as well as for validation steps where I initialize the metrics. Basically the metric...
Hi @SkafteNicki, here is the state when the error happens: ``` {'similarity': metatensor(105.5943, device='cuda:0'), 'total': tensor(101., device='cuda:0')} ``` I'll further scale all input tensors to the same range and see...
Hi @SkafteNicki, I have tried rescaling the range of inputs to [0, 1] (see below) but I still encountered the SSIM > 1. I am setting the `data_range` to None,...
@SkafteNicki Hello and I am sorry for the late update. I might have an idea why SSIM is larger than 1. I inspected my evaluation script and found that the...
It's likely related to this issue #2833 and #3754
@CPBridge I have a more or less similar issue when overlaying the seg mask on OHIF viewer. It is a seg file from a multiframe source image that has annotation...
@CPBridge: I'm using OHIF v3.8.3. I have tried calling the `get_pixels_by_source_frame` and the returned array is correct. The segmentation file is exported with empty slices. So it seems to me...
@fedorov Like @CPBridge said, the image I used is from the test files of highdicom, and I created a dummy segmentation for it. The overlaid segmentation you show is the...
Recognizing custom model result is bad compared to text predicted during training for Greek Language
@vamshi-1611 @bh1nv have you found the cause or solution? I also have the same problem.