[Data loss] Convolutional Block (1x1) with stride > 1 in ResNet50

Hi Coursera community,

I have a question to made clear, that is in ResNet50, some convolutional block is initialized with 1x1 kernel size but stride > 1. As I know 1x1 convolution helps to reduce the number of filters, but stride > 1 will cause some pixels to be lost?

I hope to receive helps from you guys,


It is an excellent point that has been brought up before. Here’s an earlier thread.

It is clearly just ignoring some of the data. It would seem that doing a 2x pooling layer would be a better strategy but it is what it is. The only thing I can suggest is to go read the ResNet papers and see if they comment on this.