ReLU6

2000년 도입 · 논문 95편에서 사용

ReLU6 is a modification of the rectified linear unit where we limit the activation to a maximum size of $6$. This is due to increased robustness when used with low-precision computation. Image Credit: PyTorch

출처: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

소개 논문: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications