我有一个sklearn.svm.svc(RBF核)模型训练在两个类上,每个类包含140个样本。当我试图预测时,概率设置为true,这两个类的预测概率是不同的。在对于某些测试样本,它给出的概率大于1
其他不到一个
例如:“样品1”:1.55478334,“样品2”:
0.999984)。
在某些情况下,它给出的两个概率都小于1
例如
(“样品-1”:0.418229494776875,“样品-2”:
0.58177035052223113)。
我的代码如下:#Training code
tcdf512_d1=np.empty(280,(18)),dtype=float)
lables=np.empty((0))
model512_d1=SVC(probability=True)
for img,img2 in map(None,catA,catB):
if img!=None:
tcdf512_d1[k]=img(18 features i.e. skewness,variance, standard deviation etc)
k+=1
lables=np.append(lables,'Cat-VI')
pass
if img2!=None:
tcdf512_d1[k]=img2(18 features i.e. skewness,variance, standard deviation etc)
k+=1
lables=np.append(lables,'Cat-VII')
pass
if k%50==0:
print (k)
print ("LBP Calculated")
print (time.strftime('%d/%m/%Y %H:%M:%S'))
model512_d1.fit(tcdf512_d1,lables)
tcdf512_d1=None
lables=None
k=None
print ("Model Trained")
print (time.strftime('%d/%m/%Y %H:%M:%S'))
joblib.dump(model512_d1,"Cat/momentsCat_6-7_128_d1.pkl",compress=3)
print ("Model Saved")
print (time.strftime('%d/%m/%Y %H:%M:%S'))
model512_d1=None
#Testing Code
size=128
Cat_I_II = joblib.load("Cat/momentsCat_6-7_128_d1.pkl")
name1="VII"
print (name1)
images_address="Catagory/Testbg/"+name1+"/"
name1="Cat-"+str(name1)
test_images = cvutils.imlist(images_address)
count =images_address.rfind("/")+1
results1=[]
print (len(test_images))
print ("Start Time ")
print (time.strftime('%d/%m/%Y %H:%M:%S'))
j=float(len(test_images))
k=0
# testdata=[]
for img3 in test_images:
results1.append("Image : "+str(img3[count:]))
results1.append("\n")
varientarray=[]
array=[]
array.append(img3(18 features i.e. skewness,variance, standard deviation etc))
print array
prediction = Cat_I_II.predict(array)[0]
prob=Cat_I_II.predict_proba(array)[0]
prob_per_class_dictionary = dict(zip(Cat_I_II.classes_, prob))
print(prediction,prob_per_class_dictionary)
results1.append("Result of Cat_I_II is : "+str(prediction) +"\t"+str(prob_per_class_dictionary))
varientarray.append(prediction)
print (k)
print ("Final Result of image "+str(i[count:]) + " is : "+str(collections.Counter(varientarray).most_common(1)[0][0]))
results1.append("Final Result of image "+str(i[count:]) + " is : "+str(collections.Counter(varientarray).most_common(1)[0][0]))
if str(i[count:i.index('0')])==collections.Counter(varientarray).most_common(1)[0][0]:
j-=1
gc.collect()
k+=1
k=float(j*100/len(test_images))
Accuracy=float((len(test_images)-j)*100/len(test_images))
print (j)
print (k)
print (Accuracy)
with open("CatResults/_Finalresults.txt", 'a') as f:
f.write(str("The accuracy for "+str(name1)+" is :"+str(Accuracy)) +"\n")
results1.append("Incorrect Results are :"+str(j))
results1.append("The percentage of incorrect result is :"+str(k))
results1.append("The accuracy is :"+str(Accuracy))
with open("CatResults/Cat-"+str(name1)+"resultsp2.txt", 'w') as f:
for s in results1:
f.write(str(s) +"\n")
print ("End Time")
print(time.strftime('%d/%m/%Y %H:%M:%S'))
我的结果片段如下