DeepMed-Lab-ECNU / BCP

Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation (CVPR 2023)
MIT License
158 stars 15 forks source link

about pre_train and self_train #47

Open xie-D-xq opened 2 weeks ago

xie-D-xq commented 2 weeks ago

You did a great job ! I have a question, what is the difference between self_training and pre_training ? why do I get an error when I choose to call pre_training weights instead of self_training weights in the test file ? Error reported as follows:

屏幕截图 2024-11-06 211720

byhwhite commented 4 days ago

Models of pre_train and self_train saved in different ways. You could change the load_net function in test file to that used in self_train, which could load pre_train model correctly.