Ibraheem Al-Dhamari

Tried different reader. with 256,256,130 and 1,1,1.3 I got index range error but it works with 256,256,256 and 1,1,1.3, the result doesn ot look good  this is the modified...

I think when you write the result you use the default values not the one of the input image, in my case: input: size:256,256,256 spacing:1,1,0.66 origin: -86.6,133.9,116.7 result: size:256,256,256 spacing:1,1,1...

Thanks for the info.

> Hi, I noticed that you hace successfully run the code thongh loss_net = nan. I'm wondering if you have come across the bug "No module named 'utils.io'" even after...

> rge node with control input: StatefulPartitionedCall/unet/unet_avg_linear3d/expanding0/dropout_3/cond/branch_executed/_1267 > 2023-04-28 00:39:47.636940: W tensorflow/compiler/jit/xla_device.cc:398] XLA_GPU and XLA_CPU devices are deprecated and will be removed in subsequent releases. Instead, use either @tf.function(experimental_compile=True) for...

> When training main_spine_localization.py, loss_net = nan. I had check all parameter,but all this. Do you know why? thank you > > 09:37:40: train iter: 0 loss_net: 0.3521 norm: 4.5986...

I noticed the values for the same image have been change d e.g.: **GL003:** #Old setup: 65.72, 34.24, 243.03, 64.46, 32.72, 224.24, 65.29, 31.73, 204.38, 66.04, 32.67, 186.84, 66.89, 33.50,...

> Hi I have the same problem with you. Did you solve it yet? I am using the old datasets from 2019 for now and it seems to work. I...

You may need to check the original dataset authors, here is a related issue: https://github.com/anjany/verse/issues/3

Strang, please provide the complete error message. I think it is not used anymore [check here](https://github.com/christianpayer/MedicalDataAugmentationTool-VerSe/blob/51569f9680e34b0e6dd74bc33587204cf4b2afdf/verse2020/training/main_vertebrae_segmentation.py#L116).