def main():
yolo = YOLO(class_num, anchors)
# Placeholder:0
inputs = tf.compat.v1.placeholder(dtype=tf.float32, shape=[1, None, None, 3])
feature_y1, feature_y2, feature_y3 = yolo.forward(inputs, isTrain=False)
# concat_9:0, concat_10:0, concat_11:0
pre_boxes, pre_score, pre_label = yolo.get_predict_result(feature_y1, feature_y2, feature_y3, 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(ckpt_file_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
Log.add_log("message: ckpt model:'"+str(ckpt.model_checkpoint_path)+"'")
else:
Log.add_log("message:no ckpt model")
exit(1)
# save PB model
out_graph = tf.graph_util.convert_variables_to_constants(sess,sess.graph_def,['Placeholder','yolo/Conv_1/BiasAdd', 'yolo/Conv_9/BiasAdd', 'yolo/Conv_17/BiasAdd', 'concat_9', 'concat_10', 'concat_11']) # "yolo/Conv_13/BiasAdd"
saver_path = tf.train.write_graph(out_graph,"",pd_dir,as_text=False)
print("saver path: ",saver_path)
def main():
yolo = YOLO()
inputs = tf.compat.v1.placeholder(dtype=tf.float32, shape=[1, None, None, 3])
feature_y1, feature_y2, feature_y3 = yolo.forward(inputs, class_num, isTrain=False)
pre_boxes, pre_score, pre_label = get_predict_result(feature_y1, feature_y2, feature_y3,
anchors[2], anchors[1], anchors[0],
width, height, class_num,
score_thresh=score_thresh,
iou_thresh=iou_thresh,
max_box=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(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)
# assert(0)
# dictionary of name of corresponding id
word_dict = tools.get_word_dict(name_file)
# dictionary of per names
color_table = tools.get_color_table(class_num)
for name in os.listdir(val_dir):
img_name = path.join(val_dir, name)
if not path.isfile(img_name):
print("'%s' is not file" %img_name)
continue
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")
continue
start = time.perf_counter()
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 save_img:
write_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
yolo = YOLO(80, 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, 80,
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("./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)
# 名字字典
word_dict = tools.get_word_dict("./data/coco.names")
# 色表
color_table = tools.get_color_table(80)
width = 608
height = 608
val_dir = "./coco_test_img"
for name in os.listdir(val_dir):
img_name = path.join(val_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:
continue
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)
save_img(img_ori, name)
def main():
yolo = YOLO(config.class_num, config.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.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.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.name_file)
# 色表
color_table = tools.get_color_table(config.class_num)
width = config.width
height = config.height
for name in os.listdir(config.val_dir):
img_name = path.join(config.val_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)
def convert_weight(model_path, output_dir, size=608):
save_path = os.path.join(output_dir, 'YOLO_v4_' + str(size) + '.ckpt')
class_num = 80
yolo = YOLO()
with tf.Session() as sess:
tf_input = tf.placeholder(tf.float32, [1, size, size, 3])
feature = yolo.forward(tf_input, class_num, isTrain=False)
saver = tf.train.Saver(var_list=tf.global_variables())
load_ops = load_weights(tf.global_variables(), model_path)
sess.run(load_ops)
saver.save(sess, save_path=save_path)
print('YOLO v4 weights have been transformed to {}'.format(save_path))
def backward():
yolo = YOLO(config.class_num,
config.anchors,
width=config.width,
height=config.height)
data = Data(config.train_file,
config.class_num,
config.batch_size,
config.anchors,
config.multi_scale_img,
width=config.width,
height=config.height)
inputs = tf.compat.v1.placeholder(dtype=tf.float32,
shape=[config.batch_size, None, None, 3])
y1_true = tf.compat.v1.placeholder(
dtype=tf.float32,
shape=[config.batch_size, None, None, 3, 4 + 1 + config.class_num])
y2_true = tf.compat.v1.placeholder(
dtype=tf.float32,
shape=[config.batch_size, None, None, 3, 4 + 1 + config.class_num])
y3_true = tf.compat.v1.placeholder(
dtype=tf.float32,
shape=[config.batch_size, None, None, 3, 4 + 1 + config.class_num])
feature_y1, feature_y2, feature_y3 = yolo.forward(
inputs, weight_decay=config.weight_decay, isTrain=True)
global_step = tf.Variable(0, trainable=False)
# 损失 yolov4
loss = yolo.get_loss_v4(feature_y1, feature_y2, feature_y3, y1_true,
y2_true, y3_true, config.cls_normalizer,
config.ignore_thresh, config.prob_thresh,
config.score_thresh)
l2_loss = tf.compat.v1.losses.get_regularization_loss()
epoch = compute_curr_epoch(global_step, config.batch_size,
len(data.imgs_path))
lr = config_lr(config.lr_type, config.lr_init, epoch)
optimizer = config_optimizer(config.optimizer_type, lr, config.momentum)
update_ops = tf.compat.v1.get_collection(tf.compat.v1.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
gvs = optimizer.compute_gradients(loss + l2_loss)
clip_grad_var = [
gv if gv[0] is None else [tf.clip_by_norm(gv[0], 100.), gv[1]]
for gv in gvs
]
train_step = optimizer.apply_gradients(clip_grad_var,
global_step=global_step)
# 初始化
init = tf.compat.v1.global_variables_initializer()
saver = tf.compat.v1.train.Saver()
with tf.compat.v1.Session() as sess:
sess.run(init)
step = 0
ckpt = tf.compat.v1.train.get_checkpoint_state(config.model_path)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
step = eval(step)
Log.add_log("message:存在 ckpt 模型, global_step=" + str(step))
else:
Log.add_log("message:不存在 ckpt 模型")
# 一共迭代这么多次
total_steps = np.ceil(config.total_epoch * len(data.imgs_path) /
config.batch_size)
while step < total_steps:
start = time.perf_counter()
batch_img, y1, y2, y3 = next(data)
_, loss_, step, lr_ = sess.run([train_step, loss, global_step, lr],
feed_dict={
inputs: batch_img,
y1_true: y1,
y2_true: y2,
y3_true: y3
})
end = time.perf_counter()
print(
"step: %6d, loss: %.5g\t, w: %3d, h: %3d, lr:%.5g\t, time: %5f s"
% (step, loss_, data.width, data.height, lr_, end - start))
if step % 5 == 2:
Log.add_loss(str(step) + "\t" + str(loss_))
if (step + 1) % config.save_step == 0:
Log.add_log("message:当前运行模型保存, step=" + str(step) + ", lr=" +
str(lr_))
saver.save(sess,
path.join(config.model_path, config.model_name),
global_step=0)
Log.add_log("message:训练完成保存模型, step=" + str(step))
saver.save(sess,
path.join(config.model_path, config.model_name),
global_step=step)
return 0
def main():
class_num = 80
width = 608
height = 608
score_thresh = 0.5
iou_thresh = 0.213
max_box = 50
anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
anchors = np.asarray(anchors).astype(np.float32).reshape([-1, 3, 2])
model_dir = "./yolo_weights"
name_file = "./data/coco.names"
val_dir = "./coco_test_img"
yolo = YOLO()
inputs = tf.compat.v1.placeholder(dtype=tf.float32,
shape=[1, None, None, 3])
feature_y1, feature_y2, feature_y3 = yolo.forward(inputs,
class_num,
isTrain=False)
pre_boxes, pre_score, pre_label = get_predict_result(
feature_y1,
feature_y2,
feature_y3,
anchors[2],
anchors[1],
anchors[0],
width,
height,
class_num,
score_thresh=score_thresh,
iou_thresh=iou_thresh,
max_box=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(model_dir)
if ckpt and ckpt.model_checkpoint_path:
print("restore model from ", ckpt.model_checkpoint_path)
saver.restore(sess, ckpt.model_checkpoint_path)
else:
print("can not find ckpt model")
assert (0)
# id to names
word_dict = tools.get_word_dict(name_file)
# color of corresponding names
color_table = tools.get_color_table(class_num)
for name in os.listdir(val_dir):
img_name = path.join(val_dir, name)
if not path.isfile(img_name):
print("'%s' is not a file" % img_name)
continue
start = time.perf_counter()
img, img_ori = read_img(img_name, width, height)
if img is None:
continue
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)
save_img(img_ori, name)
def backward():
class_num = config.voc_class_num
yolo = YOLO(class_num,
config.voc_anchors,
width=config.width,
height=config.height)
data = Data(config.voc_root_dir,
config.voc_dir_ls,
"./data/voc.names",
class_num,
config.batch_size,
config.voc_anchors,
config.data_augment,
config.width,
config.height,
data_debug=config.data_debug)
inputs = tf.compat.v1.placeholder(dtype=tf.float32,
shape=[config.batch_size, None, None, 3])
y1_true = tf.compat.v1.placeholder(
dtype=tf.float32,
shape=[config.batch_size, None, None, 3, 4 + 1 + class_num])
y2_true = tf.compat.v1.placeholder(
dtype=tf.float32,
shape=[config.batch_size, None, None, 3, 4 + 1 + class_num])
y3_true = tf.compat.v1.placeholder(
dtype=tf.float32,
shape=[config.batch_size, None, None, 3, 4 + 1 + class_num])
feature_y1, feature_y2, feature_y3 = yolo.forward(
inputs, weight_decay=config.weight_decay, isTrain=True)
global_step = tf.Variable(0, trainable=False)
# 损失 yolov4
loss = yolo.get_loss_v4(feature_y1, feature_y2, feature_y3, y1_true,
y2_true, y3_true, config.cls_normalizer,
config.ignore_thresh, config.prob_thresh,
config.score_thresh)
l2_loss = tf.compat.v1.losses.get_regularization_loss()
epoch = compute_curr_epoch(global_step, config.batch_size, data.num_imgs)
lr = config_lr(config.lr_type, config.lr_init, epoch)
optimizer = config_optimizer(config.optimizer_type, lr, config.momentum)
update_ops = tf.compat.v1.get_collection(tf.compat.v1.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
gvs = optimizer.compute_gradients(loss + l2_loss)
clip_grad_var = [
gv if gv[0] is None else [tf.clip_by_norm(gv[0], 100.), gv[1]]
for gv in gvs
]
train_step = optimizer.apply_gradients(clip_grad_var,
global_step=global_step)
# 初始化
init = tf.compat.v1.global_variables_initializer()
saver = tf.compat.v1.train.Saver()
with tf.compat.v1.Session() as sess:
sess.run(init)
step = 0
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)
step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
step = eval(step)
Log.add_log("message:存在 ckpt 模型, global_step=" + str(step))
else:
Log.add_log("message:不存在 ckpt 模型")
# 一共迭代这么多次
total_steps = np.ceil(config.total_epoch * data.num_imgs /
config.batch_size)
while step < total_steps:
start = time.perf_counter()
batch_img, y1, y2, y3 = next(data)
_, loss_, step, lr_ = sess.run([train_step, loss, global_step, lr],
feed_dict={
inputs: batch_img,
y1_true: y1,
y2_true: y2,
y3_true: y3
})
end = time.perf_counter()
print(
"step: %6d, loss: %.5g\t, w: %3d, h: %3d, lr:%.5g\t, time: %5f s"
% (step, loss_, data.width, data.height, lr_, end - start))
if (loss_ > 1e3) and (step > 1e3):
Log.add_log("error:loss exception, loss_value = " + str(loss_))
''' break the process or lower learning rate '''
raise ValueError("error:loss exception, loss_value = " +
str(loss_) +
", please lower your learning rate")
# lr = tf.math.maximum(tf.math.divide(lr, 10), config.lr_lower)
if step % 5 == 2:
Log.add_loss(str(step) + "\t" + str(loss_))
if (step + 1) % config.save_step == 0:
if config.save_ckpt_model:
# save ckpt model
Log.add_log("message: save ckpt model, step=" + str(step) +
", lr=" + str(lr_))
saver.save(sess,
path.join(config.voc_model_path,
config.voc_model_name),
global_step=step)
if config.save_pb_model:
Log.add_log("message: save pb model, step=" + str(step) +
", lr=" + str(lr_))
pb_model_name = path.join(
config.voc_model_path,
config.voc_model_name) + '-' + str(step) + ".pb"
constant_graph = graph_util.convert_variables_to_constants(
sess, sess.graph_def, [
'yolo/Conv_1/BiasAdd', 'yolo/Conv_9/BiasAdd',
'yolo/Conv_17/BiasAdd'
])
# save PB model
with tf.gfile.FastGFile(pb_model_name, mode='wb') as f:
f.write(constant_graph.SerializeToString())
# save ckpt model
if config.save_ckpt_model:
Log.add_log("message: save final ckpt model, step=" + str(step))
saver.save(sess,
path.join(config.voc_model_path, config.voc_model_name),
global_step=step)
# save pb model
if config.save_pb_model:
Log.add_log("message: save final pb model, step=" + str(step))
pb_model_name = path.join(
config.voc_model_path,
config.voc_model_name) + '-' + str(step) + ".pb"
constant_graph = graph_util.convert_variables_to_constants(
sess, sess.graph_def, [
'yolo/Conv_1/BiasAdd', 'yolo/Conv_9/BiasAdd',
'yolo/Conv_17/BiasAdd'
])
# save PB model
with tf.gfile.FastGFile(pb_model_name, mode='wb') as f:
f.write(constant_graph.SerializeToString())
return 0
def backward():
yolo = YOLO()
data = Data(voc_root_dir,
names_file,
class_num,
batch_size,
anchors,
is_tiny=False,
size=size)
inputs = tf.compat.v1.placeholder(dtype=tf.float32,
shape=[batch_size, None, None, 3])
y1_true = tf.compat.v1.placeholder(
dtype=tf.float32, shape=[batch_size, None, None, 3, 4 + 1 + class_num])
y2_true = tf.compat.v1.placeholder(
dtype=tf.float32, shape=[batch_size, None, None, 3, 4 + 1 + class_num])
y3_true = tf.compat.v1.placeholder(
dtype=tf.float32, shape=[batch_size, None, None, 3, 4 + 1 + class_num])
feature_y1, feature_y2, feature_y3 = yolo.forward(
inputs, class_num, weight_decay=weight_decay, isTrain=True)
global_step = tf.Variable(0, trainable=False)
# loss value of yolov4
loss = Loss().yolo_loss([feature_y1, feature_y2, feature_y3],
[y1_true, y2_true, y3_true],
[anchors[2], anchors[1], anchors[0]],
width,
height,
class_num,
cls_normalizer=cls_normalizer,
iou_normalizer=iou_normalizer,
iou_thresh=iou_thresh,
prob_thresh=prob_thresh,
score_thresh=score_thresh)
l2_loss = tf.compat.v1.losses.get_regularization_loss()
epoch = compute_curr_epoch(global_step, batch_size, len(data.imgs_path))
lr = Lr.config_lr(lr_type, lr_init, lr_lower=lr_lower, \
piecewise_boundaries=piecewise_boundaries, \
piecewise_values=piecewise_values, epoch=epoch)
optimizer = Optimizer.config_optimizer(optimizer_type, lr, momentum)
update_ops = tf.compat.v1.get_collection(tf.compat.v1.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
gvs = optimizer.compute_gradients(loss + l2_loss)
clip_grad_var = [
gv if gv[0] is None else [tf.clip_by_norm(gv[0], 100.), gv[1]]
for gv in gvs
]
train_step = optimizer.apply_gradients(clip_grad_var,
global_step=global_step)
# initialize
init = tf.compat.v1.global_variables_initializer()
saver = tf.compat.v1.train.Saver()
with tf.compat.v1.Session() as sess:
sess.run(init)
step = 0
ckpt = tf.compat.v1.train.get_checkpoint_state(model_path)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
step = eval(step)
Log.add_log("message: load ckpt model, global_step=" + str(step))
else:
Log.add_log("message:can not fint ckpt model")
curr_epoch = step // data.steps_per_epoch
while curr_epoch < total_epoch:
for _ in range(data.steps_per_epoch):
start = time.perf_counter()
batch_img, y1, y2, y3 = next(data)
_, loss_, step, lr_ = sess.run(
[train_step, loss, global_step, lr],
feed_dict={
inputs: batch_img,
y1_true: y1,
y2_true: y2,
y3_true: y3
})
end = time.perf_counter()
if (loss_ > 1e3) and (step > 1e3):
Log.add_log("error:loss exception, loss_value = " +
str(loss_))
''' break the process or lower learning rate '''
raise ValueError("error:loss exception, loss_value = " +
str(loss_) +
", please lower your learning rate")
# lr = tf.math.maximum(tf.math.divide(lr, 10), config.lr_lower)
if step % 5 == 2:
print(
"step: %6d, epoch: %3d, loss: %.5g\t, wh: %3d, lr:%.5g\t, time: %5f s"
% (step, curr_epoch, loss_, width, lr_, end - start))
Log.add_loss(str(step) + "\t" + str(loss_))
curr_epoch += 1
if curr_epoch % save_per_epoch == 0:
# save ckpt model
Log.add_log("message: save ckpt model, step=" + str(step) +
", lr=" + str(lr_))
saver.save(sess,
path.join(model_path, model_name),
global_step=step)
Log.add_log("message: save final ckpt model, step=" + str(step))
saver.save(sess, path.join(model_path, model_name), global_step=step)
return 0
def main():
yolo = YOLO(config.class_num, config.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.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.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 fint ckpt model")
# exit(1)
# dictionary of name of corresponding id
word_dict = tools.get_word_dict(config.name_file)
# dictionary of per names
color_table = tools.get_color_table(config.class_num)
width = config.width
height = config.height
for name in os.listdir(config.val_dir):
img_name = path.join(config.val_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))
# show_img = tools.draw_img(show_img, boxes, score, label, word_dict, color_table)
# cv2.imshow('img', show_img)
# cv2.waitKey(0)
if config.keep_img_shape:
# 纠正坐标
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_ori', img_ori)
cv2.waitKey(0)
if config.save_img:
save_img(img_ori, name)
pass
import os
import sys
import tensorflow as tf
import numpy as np
import config
from src.YOLO import YOLO
from utils.misc_utils import load_weights
weight_path = './yolo_weights/yolov4.weights'
save_path = './yolo_weights/yolov4.ckpt'
#anchors = [10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326] #for yolov4-416
anchors = [12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401] # for yolov4.weights
class_num = 80 # for yolov4.weights
yolo = YOLO(class_num, anchors,width=608, height=608)
with tf.Session() as sess:
inputs = tf.placeholder(tf.float32, [1, 608, 608, 3])
feature = yolo.forward(inputs, isTrain=False)
saver = tf.train.Saver(var_list=tf.global_variables())
load_ops = load_weights(tf.global_variables(), weight_path)
sess.run(load_ops)
saver.save(sess, save_path=save_path)
print('TensorFlow model checkpoint has been saved to {}'.format(save_path))
def __init__(self,model_path,GPU_ratio=0.2):
#----var
JB_flow = 0
class_num = 80
height = 608#416, 608
width = 608#416, 608
score_thresh = 0.5
iou_thresh = 0.213
max_box = 50
anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
anchors = np.asarray(anchors).astype(np.float32).reshape([-1, 3, 2])
name_file = "./coco.names"
node_dict = {"input": "Placeholder:0",
"pre_boxes": "concat_9:0",
"pre_score": "concat_10:0",
"pre_label": "concat_11:0",
}
#----model extension check
if model_path[-2:] == 'pb':
sess, tf_dict = model_restore_from_pb(model_path, node_dict,GPU_ratio=GPU_ratio)
tf_input = tf_dict['input']
tf_pre_boxes = tf_dict["pre_boxes"]
tf_pre_score = tf_dict['pre_score']
tf_pre_label = tf_dict['pre_label']
else:
width = int(model_path.split("\\")[-1].split(".")[0].split("_")[-1]) # 416, 608
height = width # 416, 608
yolo = YOLO()
tf_input = tf.compat.v1.placeholder(dtype=tf.float32, shape=[1, None, None, 3])
feature_y1, feature_y2, feature_y3 = yolo.forward(tf_input, class_num, isTrain=False)
tf_pre_boxes, tf_pre_score, tf_pre_label = get_predict_result(feature_y1, feature_y2, feature_y3,
anchors[2], anchors[1], anchors[0],
width, height, class_num,
score_thresh=score_thresh,
iou_thresh=iou_thresh,
max_box=max_box)
init = tf.compat.v1.global_variables_initializer()
saver = tf.train.Saver()
#----GPU ratio setting
config = tf.ConfigProto(log_device_placement=True, # 印出目前的運算是使用CPU或GPU
allow_soft_placement=True, # 當設備不存在時允許tf選擇一个存在且可用的設備來繼續執行程式
)
if GPU_ratio is None:
config.gpu_options.allow_growth = True # 依照程式執行所需要的資料來自動調整
else:
config.gpu_options.per_process_gpu_memory_fraction = GPU_ratio # 手動限制GPU資源的使用
sess = tf.compat.v1.Session(config=config)
sess.run(init)
saver.restore(sess, model_path[:-5])
print("JB> Height: {}, width: {}".format(height, width))
#----label to class name
label_dict = tools.get_word_dict(name_file)
#----color of corresponding names
color_table = tools.get_color_table(class_num)
#----local var to global
self.JB_flow = JB_flow # show flow
self.width = width
self.height = height
self.tf_input = tf_input
self.pre_boxes = tf_pre_boxes
self.pre_score = tf_pre_score
self.pre_label = tf_pre_label
self.sess = sess
self.label_dict = label_dict
self.color_table = color_table
def backward():
yolo = YOLO(config.class_num,
config.anchors,
width=config.width,
height=config.height)
data = Data(config.train_file,
config.class_num,
config.batch_size,
config.anchors,
config.data_augment,
width=config.width,
height=config.height,
data_debug=config.data_debug)
inputs = tf.compat.v1.placeholder(dtype=tf.float32,
shape=[config.batch_size, None, None, 3])
y1_true = tf.compat.v1.placeholder(
dtype=tf.float32,
shape=[config.batch_size, None, None, 3, 4 + 1 + config.class_num])
y2_true = tf.compat.v1.placeholder(
dtype=tf.float32,
shape=[config.batch_size, None, None, 3, 4 + 1 + config.class_num])
y3_true = tf.compat.v1.placeholder(
dtype=tf.float32,
shape=[config.batch_size, None, None, 3, 4 + 1 + config.class_num])
feature_y1, feature_y2, feature_y3 = yolo.forward(
inputs, weight_decay=config.weight_decay, isTrain=True)
global_step = tf.Variable(0, trainable=False)
# loss value of yolov4
loss = yolo.get_loss_v4(feature_y1, feature_y2, feature_y3, y1_true,
y2_true, y3_true, config.cls_normalizer,
config.ignore_thresh, config.prob_thresh,
config.score_thresh)
l2_loss = tf.compat.v1.losses.get_regularization_loss()
epoch = compute_curr_epoch(global_step, config.batch_size,
len(data.imgs_path))
lr = config_lr(config.lr_type, config.lr_init, epoch)
optimizer = config_optimizer(config.optimizer_type, lr, config.momentum)
update_ops = tf.compat.v1.get_collection(tf.compat.v1.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
gvs = optimizer.compute_gradients(loss + l2_loss)
clip_grad_var = [
gv if gv[0] is None else [tf.clip_by_norm(gv[0], 100.), gv[1]]
for gv in gvs
]
train_step = optimizer.apply_gradients(clip_grad_var,
global_step=global_step)
# initialize
init = tf.compat.v1.global_variables_initializer()
saver = tf.compat.v1.train.Saver()
with tf.compat.v1.Session() as sess:
sess.run(init)
step = 0
ckpt = tf.compat.v1.train.get_checkpoint_state(config.model_path)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
step = eval(step)
Log.add_log("message: load ckpt model, global_step=" + str(step))
else:
Log.add_log("message: can not find ckpt model")
total_steps = np.ceil(config.total_epoch * len(data.imgs_path) /
config.batch_size)
while step < total_steps:
start = time.perf_counter()
batch_img, y1, y2, y3 = next(data)
_, loss_, step, lr_ = sess.run([train_step, loss, global_step, lr],
feed_dict={
inputs: batch_img,
y1_true: y1,
y2_true: y2,
y3_true: y3
})
end = time.perf_counter()
print(
"step: %6d, loss: %.5g\t, w: %3d, h: %3d, lr:%.5g\t, time: %5f s"
% (step, loss_, data.width, data.height, lr_, end - start))
if (loss_ > 1e3) and (step > 1e3):
Log.add_log("error:loss exception, loss_value = " + str(loss_))
''' break the process or lower learning rate '''
raise ValueError("error:loss exception, loss_value = " +
str(loss_) +
", please lower your learning rate")
# lr = tf.math.maximum(tf.math.divide(lr, 10), config.lr_lower)
if step % 5 == 2:
Log.add_loss(str(step) + "\t" + str(loss_))
if (step + 1) % config.save_step == 0:
# save ckpt model
Log.add_log("message: save ckpt model, step=" + str(step) +
", lr=" + str(lr_))
saver.save(sess,
path.join(config.model_path, config.model_name),
global_step=step)
# save ckpt model
Log.add_log("message:save final ckpt model, step=" + str(step))
saver.save(sess,
path.join(config.model_path, config.model_name),
global_step=step)
return 0
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
import os
import sys
import tensorflow as tf
import numpy as np
import config
from src.YOLO import YOLO
from utils.misc_utils import load_weights
weight_path = './yolo_weights/yolov4.weights'
save_path = './yolo_weights/yolov4.ckpt'
anchors = [
12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459,
401
] # for yolov4.weights
class_num = 80 # for yolov4.weights
yolo = YOLO()
with tf.Session() as sess:
inputs = tf.placeholder(tf.float32, [1, 608, 608, 3])
feature = yolo.forward(inputs, class_num, isTrain=False)
saver = tf.train.Saver(var_list=tf.global_variables())
load_ops = load_weights(tf.global_variables(), weight_path)
sess.run(load_ops)
saver.save(sess, save_path=save_path)
print('TensorFlow model checkpoint has been saved to {}'.format(save_path))