-
**Describe the bug**
I tried to train a model with SwinUNETR and export the model as TorchScript for later use in monai deploy packaging, but it fails export the model.
**To Reproduce**
```pyth…
-
Hello, I meet some tough problems when loading 4D nifti files. I use the UNETR network. It seems that it can support the 4D nifti file because in_channels can be set bigger than 1 according to the cod…
-
**Describe the bug**
I'm running UNETR on my local terminal within a virtual environment.
while running my main.py file on the command line, I face this issue
**To Reproduce**
Steps to reproduce…
-
File "/home/wu/.conda/envs/nnUNet/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/wu/wyc/nnUNet/nnunetv2/tr…
-
pythonic API to set initial weights of a model from a model zoo item
for example, loading from existing bundle:
```py
my_model = monai.networks.net.SwinUNETR(...)
load_state_dict(my_model, weig…
-
Hello, I want to check whether the pretrained weigt in this `https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/swin_unetr.base_5000ep_f48_lr2e-4_pretrained.pt` link is Uni…
-
Thank you for your excellent work, and this work inspire me a lot! I have a quetions in your open-sourced code that how to generate the ‘sam3d_Plansv2.1_plans_3D.pkl’ file？
![image](https://github.c…
-
Hi,
I was reading your paper on arXiv. For Swin UNETR, I wonder if you happened to record the FPV and FNV? Right now I am training it in MONAI, but I got some very high FPV and FNV.
Thanks!
-
Hello! I ran into the same problem as someone before, but I didn't get the solution from the previous answers. I am using unetr in monai for my binary classification segmentation of stroke lesions. It…
-
Thank you for your great contribution. I'm really intetested in your work so I tried to do some experiments.
I notice that the Swin-UNETR results shown in Tabel 1 has average dice socre of 83.48. I …