jling 2018-08-31
theano库是做deep learning重要的一部分,其最吸引人的地方之一是你给出符号化的公式之后,能自动生成导数。本文使用梯度下降的方法,进行数据拟合,现在把代码贴在下方
代码块
import numpy as np import theano.tensor as T import theano import time class Linear_Reg(object): def __init__(self,x): self.a = theano.shared(value = np.zeros((1,), dtype=theano.config.floatX),name = 'a') self.b = theano.shared(value = np.zeros((1,), dtype=theano.config.floatX),name = 'b') self.result = self.a * x + self.b self.params = [self.a,self.b] def msl(self,y): return T.mean((y - self.result)**2) def regrun(rate,data,labels): X = theano.shared(np.asarray(data, dtype=theano.config.floatX),borrow = True) Y = theano.shared(np.asarray(labels, dtype=theano.config.floatX),borrow = True) index = T.lscalar() #定义符号化的公式 x = T.dscalar('x') #定义符号化的公式 y = T.dscalar('y') #定义符号化的公式 reg = Linear_Reg(x = x) cost = reg.msl(y) a_g = T.grad(cost = cost,wrt = reg.a) #计算梯度 b_g = T.grad(cost = cost, wrt = reg.b) #计算梯度 updates=[(reg.a,reg.a - rate * a_g),(reg.b,reg.b - rate * b_g)] #更新参数 train_model = theano.function(inputs=[index], outputs = reg.msl(y),updates = updates,givens = {x:X[index], y:Y[index]}) done = True err = 0.0 count = 0 last = 0.0 start_time = time.clock() while done: #err_s = [train_model(i) for i in xrange(data.shape[0])] for i in xxx: err_s = [train_model(i) ] err = np.mean(err_s) #print err count = count + 1 if count > 10000 or err <0.1: done = False last = err end_time = time.clock() print 'Total time is :',end_time -start_time,' s' # 5.12s print 'last error :',err print 'a value : ',reg.a.get_value() # [ 2.92394467] print 'b value : ',reg.b.get_value() # [ 1.81334458] if __name__ == '__main__': rate = 0.01 data = np.linspace(1,10,10) labels = data * 3 + np.ones(data.shape[0],dtype=np.float64) +np.random.rand(data.shape[0]) regrun(rate,data,labels)
其基本思想是随机梯度下降。