本文整理汇总了Python中mlp.MLP.quick_cost方法的典型用法代码示例。如果您正苦于以下问题：Python MLP.quick_cost方法的具体用法？Python MLP.quick_cost怎么用？Python MLP.quick_cost使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类mlp.MLP的用法示例。
在下文中一共展示了MLP.quick_cost方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1:
# 需要导入模块: from mlp import MLP [as 别名]
# 或者: from mlp.MLP import quick_cost [as 别名]
cg_chunk_index = cg_chunk_index+1
nll=[]
error=[]
print "Iter: %d ..."%(i), "Lambda: %f"%(mlp._lambda)
grad,train_nll,train_error = mlp.get_gradient(train_gradient_X, train_gradient_Y, batch_size)
delta, next_init, after_cost = mlp.cg(-grad, train_cg_X_cur, train_cg_Y_cur, batch_size, next_init, 1)
Gv = mlp.get_Gv(train_cg_X_cur,train_cg_Y_cur,batch_size,delta)
delta_cost = numpy.dot(delta,grad+0.5*Gv)
before_cost = mlp.quick_cost(numpy.zeros((num_param,)), train_cg_X_cur, train_cg_Y_cur, batch_size)
l2norm = numpy.linalg.norm(Gv + mlp._lambda*delta + grad)
print "Residual Norm: ",l2norm
print 'Before cost: %f, After cost: %f'%(before_cost,after_cost)
param = mlp.flatParam() + delta
mlp.packParam(param)
tune_lambda = (after_cost - before_cost)/delta_cost
if tune_lambda < 0.25:
mlp._lambda = mlp._lambda*1.5
elif tune_lambda > 0.75:
mlp._lambda = mlp._lambda/1.5