Guest User

Untitled

a guest
Jan 17th, 2019
51
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 0.33 KB | None | 0 0
  1. # if we are to reduce the spatial size, apply a CONV layer to the shortcut
  2. if red:
  3. shortcut = Conv2D(K, (1, 1), strides=stride, use_bias=False,
  4. kernel_regularizer=l2(reg))(act1)
  5.  
  6. # add together the shortcut and the final CONV
  7. x = add([conv3, shortcut])
  8.  
  9. # return the addition as the output of the ResNet module
  10. return x
Add Comment
Please, Sign In to add comment