dymbe / unet-reproducibility-project Goto Github PK

• shift

• rotation

• elastic deformations:
  Found library: https://pypi.org/project/elasticdeform/ seems to be possible problem with label deformation making the lines very blurry.

• grey value variations (probably best to just normalize)

Part of the paper that is about data augmentation:

3.1 Data Augmentation
Data augmentation is essential to teach the network the desired invariance and
robustness properties, when only few training samples are available. In case of
microscopical images we primarily need shift and rotation invariance as well as
robustness to deformations and gray value variations. Especially random elas-
tic deformations of the training samples seem to be the key concept to train
a segmentation network with very few annotated images. We generate smooth
deformations using random displacement vectors on a coarse 3 by 3 grid. The
displacements are sampled from a Gaussian distribution with 10 pixels standard
deviation. Per-pixel displacements are then computed using bicubic interpola-
tion. Drop-out layers at the end of the contracting path perform further implicit
data augmentation.

Include the dataugmentation in the generator
example here: https://pytorch.org/tutorials/beginner/data_loading_tutorial.html