Getting Name of Images at which SVM mispredicted

user_18895965 0
Viewed 25

I am working on a Binary Classification Model and i want to know the names of the Images that the model mispredicted .How can i do this ?

to_be_moved = random.sample(glob.glob("/content/COVID-19_Radiography_Dataset/COVID/images/*.png"), 1500)

label= 0
for img in tqdm(to_be_moved):
    imgstate= cv2.imread(img,0)
    resizedimage=cv2.resize(imgstate,(220,220))
    fd = hog(resizedimage, orientations=9, pixels_per_cell=(2, 2),cells_per_block=(1,1), visualize=False, multichannel=False)
    data.append([fd,label])


random.shuffle(data)
features= []
labels=[]
for feature , label in data :
  features.append(feature)
  labels.append(label) 

from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
X_train , X_test , y_train , y_test = train_test_split(features,labels, test_size=0.25)
model = SVC(C=1,kernel='linear',gamma ='auto' )
model.fit(X_train , y_train)
svm machine-learning python
1 Answers

You can extend the data tuple to include the fd , pathofimage , and label. And then after the splitting , you can then after train,test,split divide the tuple and by this you will get the path as well as the images it predicted .Remember to set the shuffle to False

user_149793930
Related