f'/home/palm/PycharmProjects/seven2/xmls/readjusted/{set_name}/',
exist_ok=True)
shutil.copy(
os.path.join(anns_path, i[:-4] + '.xml'),
f'/home/palm/PycharmProjects/seven2/xmls/readjusted/{set_name}/'
+ i[:-4] + '.xml')
continue
image = read_image_bgr(os.path.join(folder, i))
start_time = time.time()
# copy to draw ong
draw = image.copy()
draw = cv2.cvtColor(draw, cv2.COLOR_BGR2RGB)
# preprocess image for network
image = preprocess_image(image)
image, scale = resize_image(image, min_side=720, max_side=1280)
# process image
boxes, scores, labels = prediction_model.predict_on_batch(
np.expand_dims(image, axis=0))
# correct for image scale
boxes /= scale
root = ET.Element('annotation')
ET.SubElement(root, 'filename').text = i
ET.SubElement(root, 'path').text = os.path.join(folder, i)
size = ET.SubElement(root, 'size')
ET.SubElement(size, 'width').text = str(draw.shape[1])
ET.SubElement(size, 'height').text = str(draw.shape[0])
anns_path = f'/home/palm/PycharmProjects/seven2/xmls/revised/{set_name}'
exiting_anns = [os.path.basename(x) for x in os.listdir(anns_path)]
for i in os.listdir(folder):
if i[:-4] + '.xml' in exiting_anns:
continue
if 'txt' in i:
continue
image = read_image_bgr(os.path.join(folder, i))
# copy to draw ong
draw = image.copy()
draw = cv2.cvtColor(draw, cv2.COLOR_BGR2RGB)
# preprocess image for network
image = preprocess_image(image)
image, scale = resize_image(image, min_side=800, max_side=1333)
# process image
start = time.time()
boxes, scores, labels = prediction_model.predict_on_batch(np.expand_dims(image, axis=0))
print("processing time: ", time.time() - start)
# correct for image scale
boxes /= scale
root = ET.Element('annotation')
ET.SubElement(root, 'filename').text = i
ET.SubElement(root, 'path').text = os.path.join(folder, i)
size = ET.SubElement(root, 'size')
ET.SubElement(size, 'width').text = str(draw.shape[1])
ET.SubElement(size, 'height').text = str(draw.shape[0])
def resize_image(self, image):
""" Resize an image using image_min_side and image_max_side.
"""
return resize_image(image,
min_side=self.image_min_side,
max_side=self.image_max_side)
continue
found.append(p)
image = read_image_bgr(p)
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
image = np.concatenate((np.expand_dims(
image, 2), np.expand_dims(image, 2), np.expand_dims(image, 2)), 2)
# copy raw image for license plate ocr
raw_im = image.copy()
# copy to draw on
draw = image.copy()
draw = cv2.cvtColor(draw, cv2.COLOR_BGR2RGB)
# preprocess image for network
image = preprocess_image(image)
image, scale = resize_image(image, min_side=smin, max_side=smax)
# process image
start = time.time()
boxes, scores, labels = model.predict_on_batch(
np.expand_dims(image, axis=0))
ptime = time.time() - start
# correct for image scale
boxes /= scale
# visualize detections
wrong_labels = []
right_label = []
for box, score, label in zip(boxes[0], scores[0], labels[0]):
# scores are sorted so we can break