davidiommi / 3d-cyclegan-pytorch-medimaging Goto Github PK

I get the following error when I run the organize_folder_structure.py:
Traceback (most recent call last):
File "C:/Users/Desktop/code/3D-CycleGan-Pytorch-MedImaging-main/organize_folder_structure.py", line 157, in
reference_image = resample_sitk_image(reference_image, spacing=args.resolution, interpolator='linear')
File "C:\Users\Desktop\code\3D-CycleGan-Pytorch-MedImaging-main\utils\NiftiDataset.py", line 189, in resample_sitk_image
orig_pixelid)
TypeError: Execute() takes 2 positional arguments but 10 were given
and how should I fix it?
Thank you!

@davidiommi Hi, I recently focus on medical image translation. I want to obtain T1 and FLAIR modalities from T2 and T1ce modalities. Can you give me some advice?

Good Day~

I think this line may be pad_y = patch_size_y - (patch_size_y - image_array.shape[1])

also, in base_option.py, str_ids.remove(',') may have error when use just one gpu. something like if ',' in str_ids: can be add to code.

Cheers

I have multiple jpg files, it can be stacked into a 3d volume resulting in dimension ( #files * height * width ). If I convert that to a nii format, will the code work?

I have been trying to run train.py just with one iteration to make sure it is saving correctly. When I do this, it gives a ValueError because the train list length is 0. I have found that the issue is in lstFile in NiftiDataset as when this function is called from train.py it never enters the for loop.

Hi,

In google Collaboratory, the following comment appears and train.py does not work.
----------------- End -------------------
Traceback (most recent call last):
File "train.py", line 15, in
opt = TrainOptions().parse()
File "/content/drive/My Drive/Colab Notebooks/3D_CycleGAN_Project/3D-CycleGan-Pytorch-MedImaging/options/base_options.py", line 109, in parse
torch.cuda.set_device(opt.gpu_ids[0])
File "/usr/local/lib/python3.7/dist-packages/torch/cuda/init.py", line 264, in set_device
torch._C._cuda_setDevice(device)
RuntimeError: CUDA error: invalid device ordinal
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

Do you know of a better way?

Enviroments:
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2020 NVIDIA Corporation
Built on Wed_Jul_22_19:09:09_PDT_2020
Cuda compilation tools, release 11.0, V11.0.221
Build cuda_11.0_bu.TC445_37.28845127_0

Cheers,
Hisanori Yoshimura
E-mail: [email protected]