Closed 423data closed 1 day ago
@423data Thank you for the comment!
We call 1x1 convolution as Pointwise or Channelwise Convolution. For the second question first, main difference of channel-wise (==pointwise == 1x1 conv) and depthwise convolution is summarized in Issue.
For the first question, upper block is Inverted bottleneck from MobileNet v2, and the bottom one is from MobileNet v1 :) (Aplogies for the confusion)
Why is Conv_channel1 on the first slide different from Conv_channel1 on the second slide, but the type of Convolution (name?) that represents them? (channelwise Conv, pointwise Conv) They have the same components. Next, I was wondering what determines the characteristics of each convolution. At first, I thought it was the components that make up each convolution (like C_in, C_out, ...). I guess the position where the convolution is located has affected it. I look forward to hearing from the expert :)