RRPad 0.0.2

ReplicationReflectionPad combines ReplicationPad and ReflectionPad to prevent errors from being reported due to small input sizes when using non-constant padding types.

RRPad

ReplicationReflectionPad combines ReplicationPad and ReflectionPad to prevent errors from being reported due to small input sizes when using non-constant padding types.

Install

pip install RRPad

Use

from RRPad import ReplicationReflectionPad1d,ReplicationReflectionPad2d
...
pad=ReplicationReflectionPad1d(paddingSize)
input=torch.randn((1,2,3))
output=pad(input)

HomePage

https://github.com/PsycheHalo/RRPad/