def main(argv):
flags = parser(
description="freeze yolov3 graph from checkpoint file").parse_args()
print("=> the input image size is [%d, %d]" %
(flags.image_h, flags.image_w))
anchors = utils.get_anchors(flags.anchors_path, flags.image_h,
flags.image_w)
model = yolov3.yolov3(flags.num_classes, anchors)
with tf.Graph().as_default() as graph:
sess = tf.Session(graph=graph)
inputs = tf.placeholder(tf.float32,
[1, flags.image_h, flags.image_w, 3
]) # placeholder for detector inputs
print("=>", inputs)
with tf.variable_scope('yolov3'):
feature_map = model.forward(inputs, is_training=False)
boxes, confs, probs = model.predict(feature_map)
scores = confs * probs
print("=>", boxes.name[:-2], scores.name[:-2])
cpu_out_node_names = [boxes.name[:-2], scores.name[:-2]]
boxes, scores, labels = utils.gpu_nms(
boxes,
scores,
flags.num_classes,
score_thresh=flags.score_threshold,
iou_thresh=flags.iou_threshold)
print("=>", boxes.name[:-2], scores.name[:-2], labels.name[:-2])
gpu_out_node_names = [
boxes.name[:-2], scores.name[:-2], labels.name[:-2]
]
feature_map_1, feature_map_2, feature_map_3 = feature_map
saver = tf.train.Saver(var_list=tf.global_variables(scope='yolov3'))
if flags.convert:
if not os.path.exists(flags.weights_path):
url = 'https://github.com/YunYang1994/tensorflow-yolov3/releases/download/v1.0/yolov3.weights'
for i in range(3):
time.sleep(1)
print("=> %s does not exists ! " % flags.weights_path)
print("=> It will take a while to download it from %s" % url)
print('=> Downloading yolov3 weights ... ')
wget.download(url, flags.weights_path)
load_ops = utils.load_weights(tf.global_variables(scope='yolov3'),
flags.weights_path)
sess.run(load_ops)
save_path = saver.save(sess, save_path=flags.ckpt_file)
print('=> model saved in path: {}'.format(save_path))
if flags.freeze:
saver.restore(sess, flags.ckpt_file)
print('=> checkpoint file restored from ', flags.ckpt_file)
utils.freeze_graph(sess, './checkpoint/yolov3_cpu_nms.pb',
cpu_out_node_names)
utils.freeze_graph(sess, './checkpoint/yolov3_gpu_nms.pb',
gpu_out_node_names)
def rnet_detect_faces_gpu(img,
bounding_boxes,
r_model_path,
thresholds=0.7,
nms_thresholds=0.7):
with torch.no_grad():
_, rnet, _ = create_mtcnn_model(r_model_path=r_model_path)
img_boxes, bboxes = gpu_get_image_boxes(bounding_boxes, img, size=24)
probs, offsets, _ = rnet(img_boxes)
mask = (probs >= thresholds)
boxes = bboxes[mask.squeeze()]
box_regs = offsets[mask.squeeze()]
scores = probs[mask].reshape((-1, ))
if boxes.shape[0] > 0:
# print(boxes,box_regs)
boxes = gpu_calibrate_box(boxes.float(), box_regs)
# nms
keep = gpu_nms(boxes, scores, nms_thresholds)
boxes = boxes[keep]
# 将检测出的框转化成矩形
boxes = gpu_convert_to_square(boxes)
return boxes
def main(argv):
flags = parser(
description="freeze yolov3 graph from checkpoint file").parse_args()
classes = utils.read_coco_names("./data/coco.names")
num_classes = len(classes)
SIZE = flags.image_size
print("=> the input image size is [%d, %d]" % (SIZE, SIZE))
model = yolov3.yolov3(num_classes)
with tf.Graph().as_default() as graph:
sess = tf.Session(graph=graph)
inputs = tf.placeholder(
tf.float32, [1, SIZE, SIZE, 3]) # placeholder for detector inputs
with tf.variable_scope('yolov3'):
feature_map = model.forward(inputs, is_training=False)
boxes, confs, probs = model.predict(feature_map)
scores = confs * probs
print("=>", boxes, scores)
boxes, scores, labels = utils.gpu_nms(
boxes,
scores,
num_classes,
score_thresh=flags.score_threshold,
iou_thresh=flags.iou_threshold)
print("=>", boxes, scores, labels)
feature_map_1, feature_map_2, feature_map_3 = feature_map
print("=>", feature_map_1, feature_map_2, feature_map_3)
saver = tf.train.Saver(var_list=tf.global_variables(scope='yolov3'))
if flags.convert:
if not os.path.exists(flags.weights_path):
url = 'https://github.com/YunYang1994/tensorflow-yolov3/releases/download/v1.0/yolov3.weights'
for i in range(3):
time.sleep(1)
print("=> %s does not exists ! " % flags.weights_path)
print("=> It will take a while to download it from %s" % url)
print('=> Downloading yolov3 weights ... ')
wget.download(url, flags.weights_path)
load_ops = utils.load_weights(tf.global_variables(scope='yolov3'),
flags.weights_path)
sess.run(load_ops)
save_path = saver.save(sess, save_path=flags.ckpt_file)
print('=> model saved in path: {}'.format(save_path))
if flags.freeze:
saver.restore(sess, flags.ckpt_file)
print('=> checkpoint file restored from ', flags.ckpt_file)
utils.freeze_graph(sess, './checkpoint/yolov3_cpu_nms.pb',
["concat_9", "mul_6"])
utils.freeze_graph(sess, './checkpoint/yolov3_gpu_nms.pb',
["concat_10", "concat_11", "concat_12"])
utils.freeze_graph(sess, './checkpoint/yolov3_feature.pb', [
"yolov3/yolo-v3/feature_map_1",
"yolov3/yolo-v3/feature_map_2",
"yolov3/yolo-v3/feature_map_3",
])
def convert_weights(self):
print(f"=> the input image size is [{self.img_h}, {self.img_w}]")
anchors = utils.get_anchors(self.anchors_path, self.img_h, self.img_w)
model = yolov3.yolov3(self.num_classes, anchors)
with tf.Graph().as_default() as graph:
sess = tf.Session(graph=graph)
inputs = tf.placeholder(tf.float32,
[1, self.img_h, self.img_w, 1
]) # placeholder for detector inputs
print("=>", inputs)
with tf.variable_scope('yolov3'):
feature_map = model.forward(inputs,
n_filters_dn=self.n_filters_dn,
n_strides_dn=self.n_strides_dn,
n_ksizes_dn=self.n_ksizes_dn,
is_training=False)
boxes, confs, probs = model.predict(feature_map)
scores = confs * probs
print("=>", boxes.name[:-2], scores.name[:-2])
cpu_out_node_names = [boxes.name[:-2], scores.name[:-2]]
boxes, scores, labels = utils.gpu_nms(boxes, scores,
self.num_classes)
print("=>", boxes.name[:-2], scores.name[:-2], labels.name[:-2])
gpu_out_node_names = [
boxes.name[:-2], scores.name[:-2], labels.name[:-2]
]
saver = tf.train.Saver(var_list=tf.global_variables(
scope='yolov3'))
if self.convert:
load_ops = utils.load_weights(
tf.global_variables(scope='yolov3'), self.weights_dir)
sess.run(load_ops)
save_path = saver.save(sess, save_path=self.checkpoint_dir)
print(f'=> model saved in path: {save_path}')
if self.freeze:
ckpt_idx = self.checkpoint_dir + '-' + str(
self.checkpoint_step)
try:
saver.restore(sess, ckpt_idx)
except:
print(
f"Error: you tried to restore a checkpoint ({self.checkpoint_dir}) that doesn't exist."
)
print(
"Please clear the network and retrain, or load a different checkpoint by changing the steps parameter."
)
print('=> checkpoint file restored from ', ckpt_idx)
utils.freeze_graph(sess,
'../../data/checkpoint/yolov3_cpu_nms.pb',
cpu_out_node_names)
utils.freeze_graph(sess,
'../../data/checkpoint/yolov3_gpu_nms.pb',
gpu_out_node_names)
def main(argv):
flags = parser(
description="freeze yolov3 graph from checkpoint file").parse_args()
print("=> the input image size is [%d, %d]" %
(flags.image_h, flags.image_w))
anchors = utils.get_anchors(flags.anchors_path, flags.image_h,
flags.image_w)
# print(anchors)
# exit()
model = YOLOv3.yolov3(flags.num_classes, anchors)
with tf.Graph().as_default() as graph:
sess = tf.Session(graph=graph)
inputs = tf.placeholder(tf.float32,
[1, flags.image_h, flags.image_w, 3
]) # placeholder for detector inputs
print("=>", inputs)
with tf.variable_scope('yolov3'):
feature_map = model.forward(
inputs, is_training=False) # 返回3个尺度的feature_map
# 获取网络给出绝对boxes(左上角,右下角)信息, 未经过最大抑制去除多余boxes
boxes, confs, probs = model.predict(feature_map)
scores = confs * probs
print("=>", boxes.name[:-2], scores.name[:-2])
# cpu 运行是恢复模型所需要的网络节点的名字
cpu_out_node_names = [boxes.name[:-2], scores.name[:-2]]
print('cpu_out_node_names: ', cpu_out_node_names)
boxes, scores, labels = utils.gpu_nms(
boxes,
scores,
flags.num_classes,
score_thresh=flags.score_threshold,
iou_thresh=flags.iou_threshold)
print("=>", boxes.name[:-2], scores.name[:-2], labels.name[:-2])
# gpu 运行是恢复模型所需要的网络节点的名字 , 直接运算得出最终结果
gpu_out_node_names = [
boxes.name[:-2], scores.name[:-2], labels.name[:-2]
]
feature_map_1, feature_map_2, feature_map_3 = feature_map
saver = tf.train.Saver(var_list=tf.global_variables(scope='yolov3'))
if flags.freeze:
saver.restore(sess, flags.ckpt_file)
print('=> checkpoint file restored from ', flags.ckpt_file)
utils.freeze_graph(sess, '../checkpoint/yolov3_cpu_nms.pb',
cpu_out_node_names)
utils.freeze_graph(sess, '../checkpoint/yolov3_gpu_nms.pb',
gpu_out_node_names)
def onet_detect_faces_gpu(img,
bounding_boxes,
o_model_path,
thresholds=0.9,
nms_thresholds=0.7):
'''跟rnet 一样的方法'''
with torch.no_grad():
_, _, onet = create_mtcnn_model(o_model_path=o_model_path)
img_boxes, bboxes = gpu_get_image_boxes(bounding_boxes, img, size=48)
probs, offsets, landmarks = onet(img_boxes)
# filter negative boxes
mask = (probs.squeeze() >= thresholds)
boxes = bboxes[mask]
box_regs = offsets[mask]
scores = probs[mask].reshape((-1, ))
landmarks = landmarks[mask]
if boxes.shape[0] > 0:
# 计算面部地标点
landmarks = gpu_calibrate_landmarks(boxes, landmarks)
boxes = gpu_calibrate_box(boxes.float(), box_regs)
height = img.shape[2]
width = img.shape[3]
bboxes = torch.max(
torch.zeros_like(boxes, device=torch.device('cuda')), boxes)
sizes = torch.IntTensor([[width, height, width, height]] *
bboxes.shape[0]).to(torch.device('cuda'))
boxes = torch.min(bboxes.int(), sizes)
# nms
keep = gpu_nms(boxes, scores, nms_thresholds, mode='min')
boxes = boxes[keep]
landmarks = landmarks[keep]
return boxes, landmarks
def pnet_detect_faces_gpu(image,
p_model_path,
min_face_size=12.0,
thresholds=0.6,
nms_thresholds=0.7):
with torch.no_grad():
pnet, _, _ = create_mtcnn_model(p_model_path=p_model_path)
# 建立一个图像金字塔
h = image.shape[2]
w = image.shape[3]
max_face_size = min(h, w)
min_detection_size = 12
factor = 0.707 # sqrt(0.5)
# 在某种意义上，应用P-Net相当于用步幅2移动12x12窗口,
stride = 2.0
cell_size = 12
candidate_boxes = torch.empty((0, 4),
dtype=torch.float,
device=torch.device('cuda'))
candidate_scores = torch.empty((0), device=torch.device('cuda'))
candidate_offsets = torch.empty((0, 4),
dtype=torch.float,
device=torch.device('cuda'))
while min_face_size <= max_face_size:
current_scale = min_detection_size / min_face_size
min_face_size /= factor
img_h = math.ceil(h * current_scale) # 向上取整 貌似有问题哟
img_w = math.ceil(w * current_scale)
# https://www.cnblogs.com/ocean1100/p/9494640.html
# 坑：cv2 把 [n,c,h,w] --> [n,c,w,h]
resize_img = torch.nn.functional.interpolate(image,
size=(img_h, img_w),
mode='bilinear',
align_corners=True)
# prob: [n,1,m,n] offset: [n,4:(x1,y1,x2,y2),m,n]
prob, offset, _ = pnet(resize_img)
# 去掉多余的维度，[m,n]
prob = prob.squeeze()
inds = (prob >
thresholds).nonzero() # inds: [[rows_idx,clos_idx],]
# 没有发现人脸
if inds.shape[0] == 0:
continue
else:
# 边界框的转换 i:四个坐标，inds[:, 0]:图片高，inds[:, 1]:图片宽
reg_x1, reg_y1, reg_x2, reg_y2 = [
offset[0, i, inds[:, 0], inds[:, 1]] for i in range(4)
]
# [n] --> [n,4] == [n:(x1,y1,x2,y2),4]
offset = torch.stack([reg_x1, reg_y1, reg_x2, reg_y2], dim=1)
score = prob[inds[:, 0], inds[:, 1]]
# 当前的候选框 [n] --> [4,n] == [4,{n:x1,n:y1,n:x2,n:y2)]
bounding_boxes = torch.stack(
[
(stride * inds[:, 1] + 1.0), # x1
(stride * inds[:, 0] + 1.0), # y1
(stride * inds[:, 1] + cell_size + 1.0), # x2
(stride * inds[:, 0] + cell_size + 1.0), # y2
],
dim=0).transpose(0, 1).float()
bounding_boxes = torch.round(bounding_boxes.float() /
current_scale)
keep = gpu_nms(bounding_boxes, score, overlap_threshold=0.5)
bboxes = bounding_boxes[keep]
scores = score[keep]
offset = offset[keep]
candidate_boxes = torch.cat([candidate_boxes, bboxes])
candidate_scores = torch.cat([candidate_scores, scores])
candidate_offsets = torch.cat([candidate_offsets, offset])
# nms
if candidate_boxes.shape[0] != 0:
keep = gpu_nms(candidate_boxes, candidate_scores, nms_thresholds)
candidate_boxes = candidate_boxes[keep]
# 使用pnet预测的偏移量来变换边界框，根据 w、h 对 x1,y1,x2,y2 的位置进行调整
candidate_boxes = gpu_calibrate_box(candidate_boxes,
candidate_offsets)
# 将检测出的框转化成矩形
candidate_boxes = gpu_convert_to_square(candidate_boxes)
return candidate_boxes
with tf.Graph().as_default() as graph:
sess = tf.Session(graph=graph)
inputs = tf.placeholder(tf.float32, [1, image_h, image_w, 3])
print(inputs)
with tf.variable_scope('yolov3'):
feature_map = model.forward(inputs, is_training=False)
boxes ,confs, probs = model.predict(feature_map)
scores = confs * probs
print("=>", boxes.name[:-2], scores.name[:-2])
cpu_out_node_names = [boxes.name[:-2], scores.name[:-2]]
boxes, scores, labels = utils.gpu_nms(boxes, scores, num_classes,
score_thresh=score_threshold,
iou_thresh=score_threshold)
print("=>", boxes.name[:-2], scores.name[:-2], labels.name[:-2])
gpu_out_node_names = [boxes.name[:-2], scores.name[:-2], labels.name[:-2]]
feature_map_1, feature_map_2, feature_map_3 = feature_map
saver = tf.train.Saver(var_list=tf.global_variables(scope='yolov3'))
if not os.path.exists(weights_path):
print('=> weight file not exist!!!')
else:
load_ops = utils.load_weights(tf.global_variables(scope='yolov3'), weights_path)
sess.run(load_ops)
save_path = saver.save(sess, save_path=ckpt_file)
print("=> model saved in path: {}".format(save_path))