from pyxvis.io.data import load_features
from pyxvis.io.plots import show_clf_results
from pyxvis.learning.classifiers import clf_model, define_classifier
from pyxvis.learning.classifiers import train_classifier, test_classifier
(X, d, Xt,
dt) = load_features('../data/F2/F2') # load training and testing data
ss_cl = ['nn(10,)', 'nn(12,6)']
for cl_name in ss_cl:
(name, params) = clf_model(cl_name) # function name and parameters
clf = define_classifier([name, params]) # classifier definition
clf = train_classifier(clf, X, d) # classifier training
d0 = test_classifier(clf, X) # classification of training
ds = test_classifier(clf, Xt) # classification of testing
show_clf_results(clf, X, d, Xt, dt, d0, ds,
cl_name) # display results and decision lines
from pyxvis.io.data import load_features
from pyxvis.io.plots import show_confusion_matrix
from pyxvis.learning.classifiers import clf_model, define_classifier
from pyxvis.learning.classifiers import train_classifier, test_classifier
(X, d, Xt,
dt) = load_features('../data/F2/F2') # load training and testing data
# Classifier definition
ss_cl = ['dmin', 'svm-rbf(0.1,1)']
n = len(ss_cl)
for k in range(n):
(name, params) = clf_model(ss_cl[k]) # function name and parameters
clf = define_classifier([name, params]) # classifier definition
clf = train_classifier(clf, X, d) # classifier training
ds = test_classifier(clf, Xt) # classification of testing
show_confusion_matrix(dt, ds, ss_cl[k]) # display confusion matrix
(Xv, dv) = init_data(X79[0:50, :], c0) # Gun
(Xv, dv) = append_data(X, d, X80[0:50, :], c1) # Shuriken
(Xv, dv) = append_data(X, d, X81[0:50, :], c2) # Blade
(Xv, dv) = append_data(X, d, X82[0:200, :], c3) # Other
# Testing data
(Xt, dt) = init_data(X79[50:150], c0) # Gun
(Xt, dt) = append_data(X, d, X80[50:150, :], c1) # Shuriken
(Xt, dt) = append_data(X, d, X81[50:150, :], c2) # Blade
(Xt, dt) = append_data(X, d, X82[200:600, :], c3) # Other
print('training ' + cl_name + ' for ' + st + ' using ' + model_name +
' ...')
(name, params) = clf_model(cl_name) # function name and parameters
clf = define_classifier([name, params]) # classifier definition
clf = train_classifier(clf, X, d) # classifier training
ds_v = test_classifier(clf, Xv) # clasification of validation
ds_t = test_classifier(clf, Xt) # clasification of testing
print('Results - ' + st + ' (' + cl_name + ') for the detectors:')
if j < 3: # detection of three treat objects
# performance on validation subset
(pr_v, re_v) = precision_recall(dv, ds_v)
Q_v = Q_v + np.sqrt(pr_v * re_v)
print(f'Pr_val = {pr_v:.4f}')
print(f'Re_val = {re_v:.4f}')
# performance on testing subset
(pr_t, re_t) = precision_recall(dt, ds_t)
Q_t = Q_t + np.sqrt(pr_t * re_t)
print(f'Pr_test = {pr_t:.4f}')
print(f'Re_test = {re_t:.4f}')
else:
# summary of three detections