The current version has deprecated functions such as scipy.misc.imsave, and the resizing part generates unwanted values in the label masks. This triggers cuda to stop the training process due to dataloader issues.
Edits include:
changing misc functions to cv2.imwrite and cv2.imread
use of nearest neighbor resize method for preserving label integers
adding test set functionality (which could be similar to val set or contain different images)
using aug_with_sbd flag to make augmentation with SBD optional
added test set functionalities (a separate test.txt file should be made in the directory)
The current version has deprecated functions such as scipy.misc.imsave, and the resizing part generates unwanted values in the label masks. This triggers cuda to stop the training process due to dataloader issues.
Edits include:
Most important reason for proposal: It works!!!