def transform(self, Xb, yb):
temp_Xb = np.empty((Xb.shape[0], Xb.shape[1], CROP_SIZE, CROP_SIZE))
for i, x in enumerate(Xb):
x_transposed = x.transpose(1, 2, 0)
x_resized = utils.resize_rgb(x_transposed, w=CROP_SIZE, h=CROP_SIZE)
x_new = x_resized.transpose(2, 0, 1)
temp_Xb[i, :, :, :] = x_new
return temp_Xb, yb
def transform(self, Xb, yb):
temp_Xb = np.empty((Xb.shape[0], Xb.shape[1], CROP_SIZE, CROP_SIZE))
for i, x in enumerate(Xb):
x_transposed = x.transpose(1,2,0)
x_resized = utils.resize_rgb(x_transposed, w=CROP_SIZE, h=CROP_SIZE)
x_new = x_resized.transpose(2,0,1)
temp_Xb[i, :, :, :] = x_new
return temp_Xb, yb
def transform(self, Xb, yb):
# if Xb.shape[0] < 128:
# pdb.set_trace()
Xb, yb = super(FlipBatchIterator, self).transform(Xb, yb)
# X = np.empty((Xb.shape[0], 3, utils.CROP_SIZE, utils.CROP_SIZE))
# for i, x in enumerate(Xb):
# patch = utils.neural_to_cv2(x)
# patch = Augmenter.random_flip(patch)
# patch = Augmenter.random_crop(patch, (CROP_SIZE, CROP_SIZE))
# X[i, :, :,: ] = utils.cv2_to_neural(patch, w=utils.CROP_SIZE, h=utils.CROP_SIZE)
temp_Xb = np.empty((Xb.shape[0], Xb.shape[1], CROP_SIZE, CROP_SIZE))
for i, x in enumerate(Xb):
patch = x.transpose(1, 2, 0)
patch = Augmenter.random_flip(patch)
patch = Augmenter.random_crop(patch, (CROP_SIZE, CROP_SIZE))
x_resized = utils.resize_rgb(patch, w=CROP_SIZE, h=CROP_SIZE)
x_new = x_resized.transpose(2, 0, 1)
temp_Xb[i, :, :, :] = x_new
return temp_Xb, yb
def transform(self, Xb, yb):
#if Xb.shape[0] < 128:
#pdb.set_trace()
Xb, yb = super(FlipBatchIterator, self).transform(Xb, yb)
#X = np.empty((Xb.shape[0], 3, utils.CROP_SIZE, utils.CROP_SIZE))
#for i, x in enumerate(Xb):
#patch = utils.neural_to_cv2(x)
#patch = Augmenter.random_flip(patch)
#patch = Augmenter.random_crop(patch, (CROP_SIZE, CROP_SIZE))
#X[i, :, :,: ] = utils.cv2_to_neural(patch, w=utils.CROP_SIZE, h=utils.CROP_SIZE)
temp_Xb = np.empty((Xb.shape[0], Xb.shape[1], CROP_SIZE, CROP_SIZE))
for i, x in enumerate(Xb):
patch = x.transpose(1,2,0)
patch = Augmenter.random_flip(patch)
patch = Augmenter.random_crop(patch, (CROP_SIZE, CROP_SIZE))
x_resized = utils.resize_rgb(patch, w=CROP_SIZE, h=CROP_SIZE)
x_new = x_resized.transpose(2,0,1)
temp_Xb[i, :, :, :] = x_new
return temp_Xb, yb
def detect_roofs(self, img_name, in_path=None):
in_path = self.in_path if in_path is None else in_path
try:
rgb_unrotated = cv2.imread(in_path+img_name, flags=cv2.IMREAD_COLOR)
gray = cv2.cvtColor(rgb_unrotated, cv2.COLOR_BGR2GRAY)
gray = cv2.equalizeHist(gray)
if self.downsized:
rgb_unrotated = utils.resize_rgb(rgb_unrotated, h=rgb_unrotated.shape[0]/2, w=rgb_unrotated.shape[1]/2)
gray = utils.resize_grayscale(gray, w=gray.shape[1]/2, h=gray.shape[0]/2)
except IOError as e:
print e
sys.exit(-1)
else:
for roof_type, detectors in self.roof_detectors.iteritems():
for i, detector in enumerate(detectors):
for angle in self.angles:
#for thatch we only need one angle
if self.rotate_detectors[i] == False and angle>0 or (roof_type=='thatch' and angle>0):#roof_type == 'thatch' and angle>0:
continue
print 'Detecting with detector: '+str(i)
print 'ANGLE '+str(angle)
with Timer() as t:
rotated_image = utils.rotate_image(gray, angle) if angle>0 else gray
delete_image = utils.rotate_image_RGB(rgb_unrotated, angle) if angle>0 else gray
detections, _ = self.detect_and_rectify(detector, rotated_image, angle, rgb_unrotated.shape[:2], rgb_rotated=delete_image)
if self.downsized:
detections = detections*2
self.viola_detections.set_detections(roof_type=roof_type, img_name=img_name,
angle=angle, detection_list=detections, img=rotated_image)
print 'Time detection: {0}'.format(t.secs)
self.viola_detections.total_time += t.secs
if DEBUG:
rgb_to_write = cv2.imread(in_path+img_name, flags=cv2.IMREAD_COLOR)
utils.draw_detections(detections, rgb_to_write, color=(255,0,0))
cv2.imwrite('{0}{3}{1}_{2}.jpg'.format('', img_name[:-4], angle, roof_type), rgb_to_write)
return rgb_unrotated
margin_0 = np.random.randint(0, margin_0)
margin_1 = np.random.randint(0, margin_1)
min_0 = np.random.randint(0, margin_0) if margin_0 > 0 else 0
min_1 = np.random.randint(0, margin_1) if margin_1 > 0 else 0
patch = img[min_0 : (min_0 + dst_shape[0]), min_1 : (min_1 + dst_shape[1]), :]
return patch
if __name__ == "__main__":
path = utils.get_path(data_fold=utils.TRAINING, in_or_out=utils.IN)
roofs = DataLoader.get_all_patches_folder(folder_path=path, grayscale=False, merge_imgs=False)
for img_name, roof_types in roofs.iteritems():
for roof_type, roof_list in roof_types.iteritems():
print roof_type
if roof_type == "metal":
continue
for i, roof in enumerate(roof_list):
cv2.imwrite("debug/{}_{}_1_{}.jpg".format(img_name, i, "normal"), roof)
roof = utils.resize_rgb(roof, w=utils.PATCH_H, h=utils.PATCH_W)
# rotate it
# roof = Augmenter().random_full_rotation(roof)
# cv2.imwrite('debug/{}_{}_2_{}.jpg'.format(img_name, i, 'rotated'), roof)
# flip it
roof = Augmenter().random_flip(roof)
cv2.imwrite("debug/{}_{}_3_{}.jpg".format(img_name, i, "flip"), roof)
# crop it
roof = Augmenter().random_crop(roof, (utils.CROP_SIZE, utils.CROP_SIZE))
cv2.imwrite("debug/{}_{}_4_{}.jpg".format(img_name, i, "crop"), roof)
min_1:(min_1 + dst_shape[1]), :]
return patch
if __name__ == '__main__':
path = utils.get_path(data_fold=utils.TRAINING, in_or_out=utils.IN)
roofs = DataLoader.get_all_patches_folder(folder_path=path,
grayscale=False,
merge_imgs=False)
for img_name, roof_types in roofs.iteritems():
for roof_type, roof_list in roof_types.iteritems():
print roof_type
if roof_type == 'metal':
continue
for i, roof in enumerate(roof_list):
cv2.imwrite(
'debug/{}_{}_1_{}.jpg'.format(img_name, i, 'normal'), roof)
roof = utils.resize_rgb(roof, w=utils.PATCH_H, h=utils.PATCH_W)
#rotate it
#roof = Augmenter().random_full_rotation(roof)
#cv2.imwrite('debug/{}_{}_2_{}.jpg'.format(img_name, i, 'rotated'), roof)
#flip it
roof = Augmenter().random_flip(roof)
cv2.imwrite('debug/{}_{}_3_{}.jpg'.format(img_name, i, 'flip'),
roof)
#crop it
roof = Augmenter().random_crop(
roof, (utils.CROP_SIZE, utils.CROP_SIZE))
cv2.imwrite('debug/{}_{}_4_{}.jpg'.format(img_name, i, 'crop'),
roof)
def detect_roofs(self, img_name, in_path=None):
in_path = self.in_path if in_path is None else in_path
try:
rgb_unrotated = cv2.imread(in_path + img_name,
flags=cv2.IMREAD_COLOR)
gray = cv2.cvtColor(rgb_unrotated, cv2.COLOR_BGR2GRAY)
gray = cv2.equalizeHist(gray)
if self.downsized:
rgb_unrotated = utils.resize_rgb(rgb_unrotated,
h=rgb_unrotated.shape[0] / 2,
w=rgb_unrotated.shape[1] / 2)
gray = utils.resize_grayscale(gray,
w=gray.shape[1] / 2,
h=gray.shape[0] / 2)
except IOError as e:
print e
sys.exit(-1)
else:
for roof_type, detectors in self.roof_detectors.iteritems():
for i, detector in enumerate(detectors):
for angle in self.angles:
#for thatch we only need one angle
if self.rotate_detectors[i] == False and angle > 0 or (
roof_type == 'thatch' and angle > 0
): #roof_type == 'thatch' and angle>0:
continue
print 'Detecting with detector: ' + str(i)
print 'ANGLE ' + str(angle)
with Timer() as t:
rotated_image = utils.rotate_image(
gray, angle) if angle > 0 else gray
delete_image = utils.rotate_image_RGB(
rgb_unrotated, angle) if angle > 0 else gray
detections, _ = self.detect_and_rectify(
detector,
rotated_image,
angle,
rgb_unrotated.shape[:2],
rgb_rotated=delete_image)
if self.downsized:
detections = detections * 2
self.viola_detections.set_detections(
roof_type=roof_type,
img_name=img_name,
angle=angle,
detection_list=detections,
img=rotated_image)
print 'Time detection: {0}'.format(t.secs)
self.viola_detections.total_time += t.secs
if DEBUG:
rgb_to_write = cv2.imread(in_path + img_name,
flags=cv2.IMREAD_COLOR)
utils.draw_detections(detections,
rgb_to_write,
color=(255, 0, 0))
cv2.imwrite(
'{0}{3}{1}_{2}.jpg'.format(
'', img_name[:-4], angle, roof_type),
rgb_to_write)
return rgb_unrotated