TransSeg
TransSeg copied to clipboard
yuhui-zh15
Official Code Release for "Adapting Pre-trained Vision Transformers from 2D to 3D through Weight Inflation Improves Medical Image Segmentation" (ML4H 2022)
Solving environment: failed ResolvePackageNotFound: - libffi==3.3=he6710b0_2 - _openmp_mutex==4.5=1_gnu - readline==8.1=h27cfd23_0 - ncurses==6.2=he6710b0_1 - xz==5.2.5=h7b6447c_0 - openssl==1.1.1l=h7f8727e_0 - bandit==1.7.1=py38h578d9bd_0 - yaml==0.2.5=h516909a_0 - tk==8.6.10=hbc83047_0 - pip==21.0.1=py38h06a4308_0 - libgomp==9.3.0=h5101ec6_17 - setuptools==58.0.4=py38h06a4308_0 - stevedore==3.5.0=py38h578d9bd_1...
Hi, Thanks a lot for your repo! I have 224x224x320 3D data that I want to finetune on, and I'm wondering if your inflation code allows for a smaller depth...
Hey, do you have also your pretrained weights of the resulting model? Becauso I would like to use your model for CLS extraction
Metadata
Owner
Metadata
Official Code Release for "Adapting Pre-trained Vision Transformers from 2D to 3D through Weight Inflation Improves Medical Image Segmentation" (ML4H 2022)