The general flow of data for an inception block is:
input data -> bottleneck -> [filters of different sizes] -> output
In your implementation, the filters of different sizes are applied sequentially like this:
input data -> bottleneck -> filter_size_a -> filter_size_b -> filter_size_c -> output
In the actual implementation the flow is something like the following.
input data -> bottleneck -> { -> filter_size_a -> } -> concat-> output
-> filter_size_b ->
-> filter_size_c ->
-> max_pool_filter ->
The general flow of data for an inception block is:
In your implementation, the filters of different sizes are applied sequentially like this:
In the actual implementation the flow is something like the following.