Maxlo24 / AMASSS_CBCT

Automatic segmentation of CBCT scans with a 3D Unet
35 stars 8 forks source link

RuntimeError UNETR #3

Closed cogitas3d closed 8 months ago

cogitas3d commented 8 months ago

Hey there!

I follow the documentation, install all packs on Ubuntu 20.04, and even running on different python versions, the error is the same.

The command: python3 ~/Programs/AMASSS_CBCT-main/MULTI_SEG/src/predict_CBCTSeg.py -i ~/del/GRAVALOS/4_NII_GZ -o ~/del/GRAVALOS/4_NII_GZ_OUT/ -dm /home/xxx/Programs/AMASSS_CBCT-main/Models -ss MAND MAX CB CV UAW -vtk True

ERROR Python3.7

Loading model /home/xxx/Programs/AMASSS_CBCT-main/Models/seg_FF_model.pth Traceback (most recent call last): File "/home/xxx/Programs/AMASSS_CBCT-main/MULTI_SEG/src/predict_CBCTSeg.py", line 498, in main(args) File "/home/xxx/Programs/AMASSS_CBCT-main/MULTI_SEG/src/predict_CBCTSeg.py", line 371, in main net.load_state_dict(torch.load(model_path,map_location=DEVICE)) File "/home/xxx/Programs/OrtogOnBlender/Blender291/2.91/python/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1224, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for UNETR: Unexpected key(s) in state_dict: "vit.patch_embedding.cls_token", "encoder2.blocks.0.1.conv3.conv.weight", "encoder2.blocks.1.1.conv3.conv.weight", "encoder3.blocks.0.1.conv3.conv.weight".

ERROR Python 3.8

Loading model /home/xxx/Programs/AMASSS_CBCT-main/Models/seg_FF_model.pth Traceback (most recent call last): File "/home/xxx/Programs/AMASSS_CBCT-main/MULTI_SEG/src/predict_CBCTSeg.py", line 498, in main(args) File "/home/xxx/Programs/AMASSS_CBCT-main/MULTI_SEG/src/predict_CBCTSeg.py", line 371, in main net.load_state_dict(torch.load(model_path,map_location=DEVICE)) File "/home/xxx/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1497, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for UNETR: Unexpected key(s) in state_dict: "vit.patch_embedding.cls_token", "encoder2.blocks.0.1.conv3.conv.weight", "encoder2.blocks.1.1.conv3.conv.weight", "encoder3.blocks.0.1.conv3.conv.weight".

Maxlo24 commented 8 months ago

Hello, I'm sorry I'm not the one taking care of that code now. Try to ask on https://github.com/DCBIA-OrthoLab/AMASSS_CBCT

cogitas3d commented 8 months ago

I solved all problems and soon I hope share the solutions.

cogitas3d commented 8 months ago

Dear @Maxlo24

I was able to use the program on three different operating systems using the OrtogOnBlender addon.

Details are available in this draft (please, use Google translator): https://ortogonline.com/doc/pt_br/OrtogOnLineMag/8/AI.html

Thank you for the material you published that made all of this possible!

AI_capa