Hi there, thank you for posting this implementation. I have a question. I am confused at why I seem to be getting 512 dimensional representations when I set include_top = False instead of 4096 dimensions. I can get 4096 dimensional representations by setting include_top = True and using the output from layer fc7, however I am curious about what is going on in the former case. The 512 dimension representations seem to perform better for the purpose of comparing face similarity too.
Hi there, thank you for posting this implementation. I have a question. I am confused at why I seem to be getting 512 dimensional representations when I set
include_top = False
instead of 4096 dimensions. I can get 4096 dimensional representations by settinginclude_top = True
and using the output from layerfc7
, however I am curious about what is going on in the former case. The 512 dimension representations seem to perform better for the purpose of comparing face similarity too.