Inception Model video

Hi in the example we have an input layer of 28X28X192, in order to preserve the dimensions we apply zero padding thats true by making stride=1 and but how does this affect the number of channels. They will remain same since max pooling is applied on 192 channels of input so we get a 28X28X192 max pooled layer and not 28X28X32 layer.

Hey @BrutalCaeser,
Apologies for the delayed response. You are correct indeed, that after applying a Max Pool layer, with padding = "same", will get you a 28 x 28 x 192 dimensional output. But as can be seen in the example below, we have applied a 1 x 1 convolutional layer afterwards, using which we have shrunk the number of output channels from 192 to 32, and hence, the final dimensions for the output are 28 x 28 x 32. I hope this helps.