ConvNet Architecture 2

Posted on 2020-09-29 | In Neural Network and Deep Learning

Words count in article: 31 | Reading time ≈ 1

InceptionNetV2

Inception V1 + Batch Normalization(BN), converge faster
After convolution / linear/ fully connected layer: $z=ReLU(BN(f(x)))$
Inreality: $z=BN(ReLU(f(x)))$

InceptionNetV3

ResNet

XceptionNet

Architecture search and compression

Transfer learning for image classification

Post author: HUANG Liu
Post link: https://huangliu0909.github.io/2020/09/29/ML_ConvNet_2/
Copyright Notice: All articles in this blog are licensed under CC BY-NC-SA 3.0 unless stating additionally.