AI-Assisted Tuberculosis Detection and Classification from Chest X-Rays Using a Deep Learning Normalization-Free Network Model

Figure 2

Different types of augmentations applied using RandAugment: (a) Original image, (b) Posterize, (c) Rotate, (d) Sharpen, (e) TranslateY, (f) ShearX, (g) ShearY, (h) Solarize, and (i) TranslateX.

(a)

(b)

(c)

(d)

(e)

(f)

(g)

(h)

(i)