search

HiLab-git / PyMIC_examples

examples of using PyMIC for medical image computing with deep learning
32 stars 4 forks source link

About training my own data #9

Closed qiyedongcode closed 1 year ago

qiyedongcode commented 2 years ago

Really exciting work! I would like to know how to use your PyMIC to complete the semi-supervised learning of my own CT data, can you make a demo?

taigw commented 2 years ago

We have already provided demos for the semi-supervised learning methods. See: https://github.com/HiLab-git/PyMIC_examples/tree/main/seg_ssl/ACDC

To use your own data, just set "root_dir" and the "train_csv", "train_csv_unlab", "valid_csv" and "test_csv" path in the configuration file, such as following:

tensor_type = float task_type = seg root_dir = ../../PyMIC_data/ACDC/preprocess/ train_csv = config/data/image_train_r10_lab.csv train_csv_unlab = config/data/image_train_r10_unlab.csv valid_csv = config/data/image_valid.csv test_csv = config/data/image_test.csv

qiyedongcode commented 1 year ago

Thank you for your reply, can you provide some cfg files for semi-supervised learning under 3D networks and preprocessing methods for ACDC datasets

taigw commented 1 year ago

Thanks for your suggestion. However, the ACDC dataset has a large inter-slice spacing and it is more suitable for using 2D networks. We will consider to provide a 3D semi-supervised segmentation demo in the following.