The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
Apache License 2.0
1.31k
stars
297
forks
source link
Found an error in the data_loader.py for lidc dataset #68
Through testing the project, I found the following code in data_loader.py for lidc dataset probably is wrong since it produces the misshapeded data.
new_img_batch.append(data[c[0]:c[1], c[2]:c[3], c[4]:tmp_c_5])
I changed it into
new_img_batch.append(data[:, c[0]:c[1], c[2]:c[3], c[4]:tmp_c_5])
hope it might help.