In ophthalmologic examinations, optical coherence tomography (OCT) images are used to measure thickness of retinal layers that is a significant criterion to diagnose ophthalmopathy. Since it is difficult even for experts to manually measure the thickness from OCT images, retinal layer segmentation methods have been investigated to detect retinal layers from OCT images. Due to lack of labeled training data, these methods cannot deal with a variety of retinal shapes and may also falsely segment background noise as retinal layers. Addressing the above problems, we propose two data augmentation methods, i.e., formula-driven data augmentation (FDDA) and partial retinal layer copying (PRLC), for retinal layer segmentation