Advanced Deep Learning with Python

Inception v1

The following diagram shows the first version of the Inception block, part of the GoogLeNet network architecture (https://arxiv.org/abs/1409.4842). GoogLeNet contains nine such Inception blocks:

Inception v1 block, inspired by https://arxiv.org/abs/1409.4842

The v1 block has four paths:

• 1×1 convolution, which acts as a kind of repeater to the input
• 1×1 convolution, followed by a 3×3 convolution
• 1×1 convolution, followed by a 5×5 convolution
• 3×3 max pooling with stride 1

The layers in the block use padding in such a way that the input and the output have the same shape (but different depths). The padding is also necessary, because ...