MCPcopy Create free account
hub / github.com/PaddlePaddle/EasyData / sample_and_apply

Function sample_and_apply

deploy/python/dataaug/data/preprocess/ops/fmix.py:167–187  ·  view source on GitHub ↗

:param x: Image batch on which to apply fmix of shape [b, c, shape*] :param alpha: Alpha value for beta distribution from which to sample mean of mask :param decay_power: Decay power for frequency decay prop 1/f**d :param shape: Shape of desired mask, list up to 3 dims :param m

(x,
                     alpha,
                     decay_power,
                     shape,
                     max_soft=0.0,
                     reformulate=False)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 1

sample_maskFunction · 0.85

Tested by

no test coverage detected