python - SVM with SKLearn & OpenCV -
i trying predict emotion shown on image using svm. when run code warning below , prediction not shown:
deprecationwarning: passing 1d arrays data deprecated in 0.17 , willraise valueerror in 0.19. reshape data either using x.reshape(-1, 1) if data has single feature or x.reshape(1, -1) if contains single sample. deprecationwarning)
here code training , testing:
emotions = ["anger", "neutral"] def make_sets(emotions): training_data = [] training_labels = [] emotion in emotions: training = glob.glob("try here\\%s\\*" %emotion) item in training: image = cv2.imread(item) gray = cv2.cvtcolor(image, cv2.color_bgr2gray) training_data.append(gray.ravel()) training_labels.append(emotions.index(emotion)) return training_data, training_labels x,y = make_sets(emotions) new_x = np.asarray(x) new_x.flatten() new_y = np.asarray(y) clf = svm.svc(kernel='linear', c=1.0) clf.fit(new_x,new_y) new_image = cv2.imread('test.jpg') gray_img = cv2.cvtcolor(new_image, cv2.color_bgr2gray) clf.predict(gray_img.ravel())
Comments
Post a Comment