Query regarding number of filters for pointwise convolutions.

[piyush-das]

Hi,

According to the paper, while calculating α(l) Ml is the number of filters in layer. However in the implementation for pointwise convolution it appears that we are using weight.shape[1] which is ideally the Cin and not the number of filters which should ideally have been weight.shape[0]. Is this by design ?

Thanks

[EkdeepSLubana]

IIRC, this was because of how dimensions are represented in pointwise filters. It may have been a design decision because it was difficult to make mobilenets work properly. Technically, benefits from orthogonality (as shown by work on mean field theory) arise when the network is overparameterized, a restriction mobilenets don't satisfy. You can find several details in the appendix of the paper.

[piyush-das]

The appendix states the following :

MobileNet-V1 has depth-separable filters that use M depthwise filters of dimensions 3×3×1 to process an input with M channels (see Figure 5). Each filter processes its corresponding channel,resulting in an output with M channels as well. This output is processed by N pointwise filters of dimensions1×1×N filters

However if previous depthwise convolutions had M output channels, the dimension of 1 pointwise convolution should have been 1x1xM and we would have had N such pointwise filters. I think the current implementation is assuming the kernel dimenstion as 1x1xN as has been mentioned in the appendix and hence weight.shape[1] == N, however ideally kernel dimension as per my understanding is 1x1xM and hence weight.shape[1] !=N [rather weight.shape[0]==N]. Is my understanding correct, or am I missing something ?

[EkdeepSLubana]

I see the point you are making and believe you are correct. In case you try it out and find it works better, please let me know and I will update the code.