def test_02_trainingse_nont(self):
images = glob.glob('train_imgs/non-vehicles/*/*.png')
(clf, scaler) = class_train.load()
counter = 0
for i in images:
img = cnst.img_read_f(i)
test_img = cv2.resize(img, (64, 64))
features = single_img_features(test_img,
color_space=cnst.color_space,
spatial_size=cnst.spatial_size,
hist_bins=cnst.hist_bins,
orient=cnst.orient,
pix_per_cell=cnst.pix_per_cell,
cell_per_block=cnst.cell_per_block,
hog_channel=cnst.hog_channel,
spatial_feat=cnst.spatial_feat,
hist_feat=cnst.hist_feat,
hog_feat=cnst.hog_feat)
test_features = scaler.transform(np.array(features).reshape(1, -1))
#test_features = features
prediction = clf.predict(test_features)
if (prediction > 0.0):
print("Prediction " + str(prediction) + " for " + i)
counter = counter + 1
print((len(images) - counter) / len(images))
def xtest_02_load(self):
r = class_train.load()
self.assertEqual(2, len(r))
print(type(r[0]))
print(type(r[1]))
self.assertIs(type(r[0]), sklearn.svm.classes.LinearSVC)
self.assertIs(type(r[1]), sklearn.preprocessing.data.StandardScaler)
def test_01_multi(self):
(svc, X_scaler) = class_train.load()
image = cnst.img_read_f('test_images/test6.jpg')
draw_image = np.copy(image)
(hw, di) = hot_windows.multi_hot_wins(image, draw_image, svc, X_scaler,
cnst.sizes)
print(hw)
mpimg.imsave("unit_test/test6_multi.jpg", di)
def test_01_ev(self):
(svc, X_scaler) = class_train.load()
image = cnst.img_read_f('test_images/test6.jpg')
for s in sizes:
draw_image = np.copy(image)
(hw, di) = hot_windows.hot_wins(image,
draw_image,
svc,
X_scaler,
xy_window=(s, s))
print(hw)
mpimg.imsave("unit_test/test6_" + str(s) + ".jpg", di)
def test_01_trainingset(self):
images = glob.glob('train_imgs/vehicles/GTI_Far/image0000.png')
(clf, scaler) = class_train.load()
for i in images:
img = cnst.img_read_f(i)
test_img = cv2.resize(img, (64, 64))
features = single_img_features(test_img,
color_space=cnst.color_space,
spatial_size=cnst.spatial_size,
hist_bins=cnst.hist_bins,
orient=cnst.orient,
pix_per_cell=cnst.pix_per_cell,
cell_per_block=cnst.cell_per_block,
hog_channel=cnst.hog_channel,
spatial_feat=cnst.spatial_feat,
hist_feat=cnst.hist_feat,
hog_feat=cnst.hog_feat)
print(features.shape)
print(features)
print(len(features))
test_features = scaler.transform(np.array(features).reshape(1, -1))
#test_features = features
prediction = clf.predict(test_features)
print(str(prediction) + " : " + i)
import numpy as np
import cv2
import class_train
import class_load
import hot_windows
import cv2
import matplotlib.image as mpimg
import numpy as np
import sys
import cnst
IMG_DIR = "project_video.mp4"
TEST_OUT = "unit_test"
(svc, X_scaler) = class_train.load()
class TestVideo(unittest.TestCase):
def test_pipe(self):
uut.process(IMG_DIR, TEST_OUT + "/L" + IMG_DIR, cb_ok) #,subC=(12,18))
def cb(img):
return img
def cb_ok(image):
draw_image = np.copy(image)
# image = image.astype(np.float32)/255