Hi,
Thanks for your great work! In the paper "Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer", you mentioned that "we used the latest checkpoint for testing and reporting results".

But i found in the file "test_2D_fully.py", only best model is be used:
save_mode_path = os.path.join( snapshot_path, '{}_best_model.pth'.format(FLAGS.model))