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

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.