【深度学习-模型系列】Inception

简介

  • [v1 - 2014] [Going Deeper with Convolutions](http://arxiv.org/abs/1409.4842)
  • [v2 - 2015] [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](http://arxiv.org/abs/1502.03167)
  • [v3 - 2015] [Rethinking the Inception Architecture for Computer Vision](http://arxiv.org/abs/1512.00567)
  • [v4 - 2016] [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](http://arxiv.org/abs/1602.07261) -- code-tensorflow
    • 尽管Inception v3与Inception-ResNet-v2都很擅长识别每一条狗所属的类别,这种新模型的性能更为显著。例如,旧模型可能会错误地将右边的图片识别为阿拉斯加雪橇犬,新模型Inception-ResNet-v2能够准确地识别两个图片中狗的类别。

创新点