斯坦福大学公开课视觉识别卷积神经网络

#assume some unit gaussian 10-D input data假设一些单位的高斯10-维输入数据
D = np.random.randn(1000, 500) #1000*500的随机初始化矩阵
hidden_layer_sizes = [500]*10 #隐藏图层尺寸 10个图层 每个图层有500个神经元
nonlinearities = ['tanh']*len(hidden_layer_sizes) #非线性=['tanh']*len([500]*10)

act = {'relu':lambda x:np.maximum(0,x), 'tanh':lambda x:np.tanh(x)} #行动{'relu':lambda x=max(0,x), 'tanh':lambda x=tanh(x)}
Hs = {}
for i in xrange(len(hidden_layer_sizes)):
  X = D if i == 0 else Hs[i-1] #input at this layer 输入该图层的数据(当i=0时X=D，否则更新为X=Hs[i-1])
  fan_in = X.shape[l] #输入_fan
  fan_out = hidden_layer_sizes[i] #输出_fan
  W = np.random.randn(fan_in, fan_out)*0.01 #layer initialization

  H = np.dot(X, W) #matrix multiply
  H = act[nonlinearities[i]](H) #nonlinearity
  Hs[i] = H #cache result on this layer

  #look at distributions at each layer
  print 'input layer had mean %f and std %f' % (np.mean(D), np.std(D))
  layer_means = [np.mean(H) for i,H in Hs.iteritems()]
  layer_stds = [np.std(H) for i,H in Hs.iteritems()]
  for i,H in Hs.iteritems():
    print 'hidden layer %d had mean %f and std %f' % (i+l, layer_means[i], layer_stds[i])

  #plot the means and standard deviations
  plt.figure()
  plt.subplot(121)
  plt.plot(Hs.keys(), layer_means, 'ob.')
  plt.title('layer mean')
  plt.subplot(122)
  plt.plot(Hs.keys), layer_stds, 'or-')
  plt.title('layer std')

  #plot the raw distributions
  plt.figure()
  for i,H in Hs.iteritems():
    plt.subplot(l, len(Hs), i+l)
    plt.(H.ravel(), 30, range(-1,1))