def parse_annotation(self, annotation):
line = annotation.split()
image_path = line[0]
if not os.path.exists(image_path):
raise KeyError("%s does not exist ... " %image_path)
image = np.array(cv2.imread(image_path))
bboxes = np.array([list(map(lambda x: int(float(x)), box.split(','))) for box in line[1:]])
if self.data_aug:
image, bboxes = self.random_horizontal_flip(np.copy(image), np.copy(bboxes))
image, bboxes = self.random_crop(np.copy(image), np.copy(bboxes))
image, bboxes = self.random_translate(np.copy(image), np.copy(bboxes))
image, bboxes = utils.image_preporcess(np.copy(image), [self.train_input_size, self.train_input_size], np.copy(bboxes))
return image, bboxes
def detect_image(pb_file, image_path, input_size=416):
return_elements = [
"input/input_data:0", "pred_sbbox/concat_2:0", "pred_mbbox/concat_2:0",
"pred_lbbox/concat_2:0"
]
with open(cfg.YOLO.CLASSES, 'r') as f:
lines = f.readlines()
num_classes = len(lines)
graph = tf.Graph()
original_image = cv2.imread(image_path)
original_image = cv2.cvtColor(original_image, cv2.COLOR_BGR2RGB)
original_image_size = original_image.shape[:2]
image_data = utils.image_preporcess(np.copy(original_image),
[input_size, input_size])
image_data = image_data[np.newaxis, ...]
return_tensors = utils.read_pb_return_tensors(graph, pb_file,
return_elements)
with tf.Session(graph=graph) as sess:
pred_sbbox, pred_mbbox, pred_lbbox = sess.run(
[return_tensors[1], return_tensors[2], return_tensors[3]],
feed_dict={return_tensors[0]: image_data})
pred_bbox = np.concatenate([
np.reshape(pred_sbbox, (-1, 5 + num_classes)),
np.reshape(pred_mbbox, (-1, 5 + num_classes)),
np.reshape(pred_lbbox, (-1, 5 + num_classes))
],
axis=0)
bboxes = utils.postprocess_boxes(pred_bbox, original_image_size,
input_size, 0.3)
bboxes = utils.nms(bboxes, 0.45, method='nms')
image = utils.draw_bbox(original_image, bboxes)
image = Image.fromarray(image)
image.show()
from PIL import Image
return_elements = [
"input/input_data:0", "pred_sbbox/concat_2:0", "pred_mbbox/concat_2:0",
"pred_lbbox/concat_2:0"
]
pb_file = "./checkpoint/yolov4.pb"
image_path = "./data/images/road.jpeg"
num_classes = 80
input_size = 416
graph = tf.Graph()
original_image = cv2.imread(image_path)
original_image = cv2.cvtColor(original_image, cv2.COLOR_BGR2RGB)
original_image_size = original_image.shape[:2]
image_data = utils.image_preporcess(np.copy(original_image),
[input_size, input_size])
image_data = image_data[np.newaxis, ...]
return_tensors = utils.read_pb_return_tensors(graph, pb_file, return_elements)
with tf.Session(graph=graph) as sess:
pred_sbbox, pred_mbbox, pred_lbbox = sess.run(
[return_tensors[1], return_tensors[2], return_tensors[3]],
feed_dict={return_tensors[0]: image_data})
pred_bbox = np.concatenate([
np.reshape(pred_sbbox, (-1, 5 + num_classes)),
np.reshape(pred_mbbox, (-1, 5 + num_classes)),
np.reshape(pred_lbbox, (-1, 5 + num_classes))
],
axis=0)
# video_path = 0
num_classes = 80
input_size = 416
graph = tf.Graph()
return_tensors = utils.read_pb_return_tensors(graph, pb_file, return_elements)
with tf.Session(graph=graph) as sess:
vid = cv2.VideoCapture(video_path)
while True:
return_value, frame = vid.read()
if return_value:
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
# image = Image.fromarray(frame)
frame_size = frame.shape[:2]
image_data = utils.image_preporcess(np.copy(frame), [input_size, input_size])
image_data = image_data[np.newaxis, ...]
prev_time = time.time()
pred_sbbox, pred_mbbox, pred_lbbox = sess.run(
[return_tensors[1], return_tensors[2], return_tensors[3]],
feed_dict={return_tensors[0]: image_data})
pred_bbox = np.concatenate([np.reshape(pred_sbbox, (-1, 5 + num_classes)),
np.reshape(pred_mbbox, (-1, 5 + num_classes)),
np.reshape(pred_lbbox, (-1, 5 + num_classes))], axis=0)
bboxes = utils.postprocess_boxes(pred_bbox, frame_size, input_size, 0.3)
bboxes = utils.nms(bboxes, 0.45, method='nms')
image = utils.draw_bbox(frame, bboxes)