Python Deep Learning - Second Edition

Inception v4 and Inception-ResNet

In the latest revision of inception networks, the authors introduce three new streamlined inception blocks that build upon the idea of the previous versions. They introduce 7 x 7 asymmetric factorized convolutions, and average pooling instead of max pooling. More importantly, they create a residual/inception hybrid network known as Inception-ResNet, where the inception blocks also include residual connections. We can see the schematic of one such block in the following diagram:

An inception block with residual skip connection

For more information about the new inception blocks and the network architectures, ...