def main():
yolo = YOLO(config.voc_class_num, config.voc_anchors)
inputs = tf.compat.v1.placeholder(dtype=tf.float32,
shape=[1, None, None, 3])
feature_y1, feature_y2, feature_y3 = yolo.forward(inputs, isTrain=False)
pre_boxes, pre_score, pre_label = yolo.get_predict_result(
feature_y1,
feature_y2,
feature_y3,
config.voc_class_num,
score_thresh=config.val_score_thresh,
iou_thresh=config.iou_thresh,
max_box=config.max_box)
init = tf.compat.v1.global_variables_initializer()
saver = tf.train.Saver()
with tf.compat.v1.Session() as sess:
sess.run(init)
ckpt = tf.compat.v1.train.get_checkpoint_state(config.voc_model_path)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
Log.add_log("message: load ckpt model:'" +
str(ckpt.model_checkpoint_path) + "'")
else:
Log.add_log("message:can not find ckpt model")
# exit(1)
# dictionary of name of corresponding id
word_dict = tools.get_word_dict(config.voc_names)
# dictionary of per names
color_table = tools.get_color_table(config.voc_class_num)
width = config.width
height = config.height
for name in os.listdir(config.voc_test_dir):
img_name = path.join(config.voc_test_dir, name)
if not path.isfile(img_name):
print("'%s' is not file" % img_name)
continue
start = time.perf_counter()
img, nw, nh, img_ori, show_img = read_img(img_name, width, height)
if img is None:
Log.add_log("message:'" + str(img) + "' is None")
boxes, score, label = sess.run([pre_boxes, pre_score, pre_label],
feed_dict={inputs: img})
end = time.perf_counter()
print("%s\t, time:%f s" % (img_name, end - start))
if config.keep_img_shape:
# modify coordinates
dw = (width - nw) / 2
dh = (height - nh) / 2
for i in range(len(boxes)):
boxes[i][0] = (boxes[i][0] * width - dw) / nw
boxes[i][1] = (boxes[i][1] * height - dh) / nh
boxes[i][2] = (boxes[i][2] * width - dw) / nw
boxes[i][3] = (boxes[i][3] * height - dh) / nh
img_ori = tools.draw_img(img_ori, boxes, score, label, word_dict,
color_table)
cv2.imshow('img', img_ori)
cv2.waitKey(0)
if config.save_img:
save_img(img_ori, name)
pass
def main():
anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 #608 anchors
#anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
yolo = YOLO(80, anchors, width=416, height=416)
inputs = tf.compat.v1.placeholder(dtype=tf.float32,
shape=[1, None, None, 3])
feature_y1, feature_y2, feature_y3 = yolo.forward(inputs, isTrain=False)
pre_boxes, pre_score, pre_label = yolo.get_predict_result(
feature_y1,
feature_y2,
feature_y3,
80,
score_thresh=config.val_score_thresh,
iou_thresh=config.iou_thresh,
max_box=config.max_box)
init = tf.compat.v1.global_variables_initializer()
saver = tf.train.Saver()
with tf.compat.v1.Session() as sess:
sess.run(init)
ckpt = tf.compat.v1.train.get_checkpoint_state("./yolo_weights")
if ckpt and ckpt.model_checkpoint_path:
print("restore: ", ckpt.model_checkpoint_path)
saver.restore(sess, ckpt.model_checkpoint_path)
else:
exit(1)
# id to names
word_dict = tools.get_word_dict("./data/coco.names")
# color of corresponding names
color_table = tools.get_color_table(80)
width = 416
height = 416
cap = cv2.VideoCapture(0)
cap.set(6, cv2.VideoWriter_fourcc('M', 'J', 'P', 'G'))
# cap.set(3, 1920)
# cap.set(4, 1080)
while True:
start = time.perf_counter()
_, frame = cap.read()
img_rgb = cv2.resize(frame, (width, height))
img_rgb = cv2.cvtColor(img_rgb, cv2.COLOR_BGR2RGB)
img_in = img_rgb.reshape((1, width, height, 3)) / 255.
#img, img_ori = read_img(img_name, width, height)
boxes, score, label = sess.run([pre_boxes, pre_score, pre_label],
feed_dict={inputs: img_in})
end = time.perf_counter()
print("time:%f s" % (end - start))
frame = tools.draw_img(frame, boxes, score, label, word_dict,
color_table)
cv2.imshow('img', frame)
if cv2.waitKey(1) & 0xFF == 27:
break
def main():
yolo = YOLO(config.voc_class_num, config.voc_anchors)
inputs = tf.compat.v1.placeholder(dtype=tf.float32,
shape=[1, None, None, 3])
feature_y1, feature_y2, feature_y3 = yolo.forward(inputs, isTrain=False)
pre_boxes, pre_score, pre_label = yolo.get_predict_result(
feature_y1,
feature_y2,
feature_y3,
config.voc_class_num,
score_thresh=config.val_score_thresh,
iou_thresh=config.iou_thresh,
max_box=config.max_box)
# 初始化
init = tf.compat.v1.global_variables_initializer()
saver = tf.train.Saver()
with tf.compat.v1.Session() as sess:
sess.run(init)
ckpt = tf.compat.v1.train.get_checkpoint_state(config.voc_model_path)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
Log.add_log("message:存在 ckpt 模型:'" +
str(ckpt.model_checkpoint_path) + "'")
else:
Log.add_log("message:不存在 ckpt 模型")
exit(1)
# 名字字典
word_dict = tools.get_word_dict(config.voc_names)
# 色表
color_table = tools.get_color_table(config.voc_class_num)
width = config.width
height = config.height
for name in os.listdir(config.voc_test_dir):
img_name = path.join(config.voc_test_dir, name)
if not path.isfile(img_name):
print("'%s'不是图片" % img_name)
continue
start = time.perf_counter()
img, img_ori = read_img(img_name, width, height)
if img is None:
Log.add_log("message:'" + str(img) + "'图片读取错误")
boxes, score, label = sess.run([pre_boxes, pre_score, pre_label],
feed_dict={inputs: img})
end = time.perf_counter()
print("%s\t, time:%f s" % (img_name, end - start))
img_ori = tools.draw_img(img_ori, boxes, score, label, word_dict,
color_table)
cv2.imshow('img', img_ori)
cv2.waitKey(0)
if config.save_img:
save_img(img_ori, name)