Update se_densenet.py - Githubissues

titu1994 / keras-squeeze-excite-network

Implementation of Squeeze and Excitation Networks in Keras

MIT License

400 stars 118 forks source link

Open ItsCRC opened 4 years ago

ItsCRC commented 4 years ago

Added ZeroPadding2D at the start before Conv2D and in subsample_initial_block to make densenet variants parameters same as original ones.

titu1994 commented 4 years ago

Same padding already does this, and adding a zero padding does not increase parameter count. Where was this stated in the paper?