当前位置: 首页>>代码示例>>Python>>正文


Python MLP.packParam方法代码示例

本文整理汇总了Python中mlp.MLP.packParam方法的典型用法代码示例。如果您正苦于以下问题:Python MLP.packParam方法的具体用法?Python MLP.packParam怎么用?Python MLP.packParam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mlp.MLP的用法示例。


在下文中一共展示了MLP.packParam方法的2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: MLP

# 需要导入模块: from mlp import MLP [as 别名]
# 或者: from mlp.MLP import packParam [as 别名]
from LR import Logisticlayer
from mlp import MLP

if __name__=="__main__":
  numpy.set_printoptions(threshold=numpy.nan)
  input_dim = 4
  output_dim = 3
  sample_size = 100
  #X=numpy.random.normal(0,1,(sample_size,input_dim))
  #temp,Y=numpy.nonzero(numpy.random.multinomial(1,[1.0/output_dim]*output_dim,size=sample_size))
 
  mlp = MLP(4,3,[10,10])
  with open('debug_nnet.pickle') as f:
    init_param = pickle.load(f)
  init_param = numpy.concatenate([i.flatten() for i in init_param])
  mlp.packParam(init_param)
  
  with open('debug_data.pickle') as f:
    data = pickle.load(f)
  X = data[0]
  Y = data[1]
  
  with open('HJv.pickle') as f:
    HJv_theano = pickle.load(f)
  num_param = numpy.sum(mlp.sizes)
  batch_size = 100
  
  grad,train_nll,train_error=mlp.get_gradient(X,Y,batch_size)
  
  
  d = 1.0*numpy.ones((num_param,))
开发者ID:lelouchmatlab,项目名称:convex-hf,代码行数:33,代码来源:check_Gv.py

示例2: xrange

# 需要导入模块: from mlp import MLP [as 别名]
# 或者: from mlp.MLP import packParam [as 别名]
    
    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

    print "Training   NNL: %f, Error: %f"%(train_nll,train_error)
    nll=[]
    error=[]
    for batch_index in xrange(n_valid_batches):
      X=valid_X[batch_index*batch_size:(batch_index+1)*batch_size,:]
      Y=valid_Y[batch_index*batch_size:(batch_index+1)*batch_size]
      mlp.forward(X)
开发者ID:lelouchmatlab,项目名称:convex-hf,代码行数:33,代码来源:test.py


注:本文中的mlp.MLP.packParam方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。