Advanced Deep Learning with Python

Inception v2 and v3

Inception v2 and v3 were released together and propose several improvements over the original Inception block (Rethinking the Inception Architecture for Computer Vision, https://arxiv.org/abs/1512.00567). The first is the factorization of the 5×5 convolution in two stacked 3×3 convolutions. We discussed the advantages of this in the Introduction to Visual Geometry Group section.

We can see the new Inception block in the following diagram:

Inception block A, inspired by https://arxiv.org/abs/1512.00567

The next improvement is the factorization of an n×n convolution in two stacked asymmetrical 1×n and n×1 convolutions. For ...