SHARE
TWEET

Untitled

a guest Jun 20th, 2019 51 Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
  1. # dout: ∂L/∂o
  2.   # a:    the input of FC layer    
  3.   # the shape of a: (batch size, hidden layer neuron)
  4.   # the shape of dw: (hidden layer neuron, num of classes)
  5.   dw = a.reshape(a.shape[0], -1).T.dot(dout)
  6.   db = np.sum(dout, axis=0)
RAW Paste Data
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy. OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!
 
Top