#lnErr = 1e-5
lnErr = 1e-2
for i in range(max+1):
err = 0.0;
for ii in range(len(input)):
err += bpn.trainEpoch(npA(input[ii]),npA(target[ii]))
if i%2500 == 0:
#if i%20 == 0:
print "iteration {0}\tError : {1:0.6f}".format(i,err)
#bpn.NN_cout("Train_"+str(i))
if err <= lnErr:
print "Min error reached at {0}".format(i)
break
#bpn.setWeights()
bpn.printWeights()
plt.figure(figsize=(10,5))
# Draw real function
x,y = samples['x'],samples['y']
plt.plot(x,y,color='b',lw=1)
# Draw network approximated function
for i in range(len(input)):
y[i] = bpn.run(npA(input[i]))
plt.plot(x,y,color='r',lw=3)
plt.axis([0,1,0,1])
plt.show()
for ii in range(len(input)):
err += bpn.trainEpoch(npA(input[ii]),npA(target[ii]))
err += bpn.trainEpoch(npA(input2[ii]),npA(target2[ii]))
if i%2500 == 0:
#if i%20 == 0:
print "iteration {0}\tError : {1:0.6f}".format(i,err)
#bpn.NN_cout("Train_"+str(i))
if err <= lnErr:
print "Min error reached at {0}".format(i)
break
#bpn.setWeights()
bpn.printWeights()
for i in range(len(input)):
output = bpn.run(npA(input[i]))
print "in :"+str(input[i])+", ou : "+str(output)
for i in range(len(input2)):
output = bpn.run(npA(input2[i]))
print "in2 :"+str(input2[i])+", ou2 : "+str(output)
#bins = bins(20,0,100)
#P.hist(v1,bins,histtype='step')
#P.hist(v1,bins,histtype='step')
"""
plt.figure(figsize=(10,5))
# Draw real function
