def main():
# load net
net_file = join(realpath(dirname(__file__)), 'SiamRPNBIG.model')
net = SiamRPNBIG()
net.load_state_dict(torch.load(net_file))
net.eval().cuda()
# warm up
for i in range(10):
net.temple(
torch.autograd.Variable(torch.FloatTensor(1, 3, 127, 127)).cuda())
net(torch.autograd.Variable(torch.FloatTensor(1, 3, 255, 255)).cuda())
# start to track
handle = vot.VOT("polygon")
Polygon = handle.region()
cx, cy, w, h = get_axis_aligned_bbox(Polygon)
image_file = handle.frame()
if not image_file:
sys.exit(0)
target_pos, target_sz = np.array([cx, cy]), np.array([w, h])
im = cv2.imread(image_file) # HxWxC
state = SiamRPN_init(im, target_pos, target_sz, net) # init tracker
while True:
image_file = handle.frame()
if not image_file:
break
im = cv2.imread(image_file) # HxWxC
state = SiamRPN_track(state, im) # track
res = cxy_wh_2_rect(state['target_pos'], state['target_sz'])
handle.report(Rectangle(res[0], res[1], res[2], res[3]))
def __init__(self, path_seq, num_frames, gt_first):
self.path_seq = path_seq
self.num_frames = num_frames
self.gt_first = gt_first
# load net
self.net = SiamRPNBIG()
# self.net.load_state_dict(torch.load("./SiamRPNBIG.model"))
self.net.eval().cuda()
#self.testing_config = testing_config
self.cur_seq_name = os.path.split(path_seq)[1]
self.cur_frame = None
class Tracker(object):
def __init__(self, path_seq, num_frames, gt_first):
self.path_seq = path_seq
self.num_frames = num_frames
self.gt_first = gt_first
# load net
self.net = SiamRPNBIG()
# self.net.load_state_dict(torch.load("./SiamRPNBIG.model"))
self.net.eval().cuda()
#self.testing_config = testing_config
self.cur_seq_name = os.path.split(path_seq)[1]
self.cur_frame = None
def on_tracking(self):
# warm up
for i in range(10):
self.net.template(
torch.autograd.Variable(torch.FloatTensor(1, 3, 127,
127)).cuda())
self.net(
torch.autograd.Variable(torch.FloatTensor(1, 3, 255,
255)).cuda())
i = 1
pred_bbx = self.gt_first
print("{}th frame: {} {} {} {}".format(i, pred_bbx[0], pred_bbx[1],
pred_bbx[2], pred_bbx[3]))
cx, cy, w, h = pred_bbx[0] + pred_bbx[2] / 2.0, pred_bbx[
1] + pred_bbx[3] / 2.0, pred_bbx[2], pred_bbx[3]
i += 1
target_pos, target_sz = np.array([cx, cy]), np.array([w, h])
im = cv2.imread(self.path_seq + '/imgs/0001.jpg') # HxWxC
state = SiamRPN_init(im, target_pos, target_sz,
self.net) # init tracker
while i <= self.num_frames:
self.index_frame = i
im = cv2.imread(self.path_seq + '/imgs/' + str(i).zfill(4) +
'.jpg')
state = SiamRPN_track(state, im)
# convert cx, cy, w, h into rect
res = cxy_wh_2_rect(state['target_pos'], state['target_sz'])
print(f"{i}th frame: ", res)
i += 1
def main(imagedir, gtdir):
# load net
net_file = join(realpath(dirname(__file__)), 'SiamRPNBIG.model')
net = SiamRPNBIG()
net.load_state_dict(torch.load(net_file))
net.eval().cuda()
# warm up
for i in range(10):
net.temple(
torch.autograd.Variable(torch.FloatTensor(1, 3, 127, 127)).cuda())
net(torch.autograd.Variable(torch.FloatTensor(1, 3, 255, 255)).cuda())
# start to track
# get the first frame groundtruth
gt_file = os.path.join(gtdir, 'gt.txt')
with open(gt_file, 'r') as f:
lines = f.readlines()
gt = []
for line in lines:
line = line.split(' ')
gt.append([int(float(x)) for x in line])
init_bbox = gt[0] # top-left x y,w,h
target_pos, target_sz = rect_2_cxy_wh(
init_bbox) # top-left x y,w,h --> center x y,w,h
image_list = glob.glob(os.path.join(imagedir, '*.jpg'))
image_list.sort()
im = cv2.imread(image_list[0]) # HxWxC
state = SiamRPN_init(im, target_pos, target_sz, net) # init tracker
bboxes = []
for i in range(1, len(gt)):
im = cv2.imread(image_list[i]) # HxWxC
state = SiamRPN_track(state, im) # track
res = cxy_wh_2_rect(
state['target_pos'],
state['target_sz']) # center x y,w,h --> top-left x y,w,h
bboxes.append(res.tolist())
_, precision, precision_auc, iou = _compile_results(gt[1:], bboxes)
print(' -- Precision ' + "(20 px)" + ': ' + "%.2f" % precision +\
' -- Precision AUC: ' + "%.2f" % precision_auc + \
' -- IOU: ' + "%.2f" % iou + ' --')
isSavebbox = True
if isSavebbox:
print('saving bbox...')
res_bbox_file = os.path.join('results_bbox.json')
json.dump(bboxes, open(res_bbox_file, 'w'), indent=2)
isSavevideo = True
if isSavevideo:
print('saving video...')
save_video(image_list, bboxes)
print('done')
def main():
# load net
net = SiamRPNBIG()
net.load_state_dict(torch.load('SiamRPNBIG.model'))
net.eval().cuda()
# warm up
for i in range(10):
net.temple(torch.autograd.Variable(torch.FloatTensor(1, 3, 127, 127)).cuda())
net(torch.autograd.Variable(torch.FloatTensor(1, 3, 255, 255)).cuda())
# start to track
cap = cv2.VideoCapture(0)
while True:
success,im=cap.read()
if success is not True:
break
cv2.imshow('cam',im)
k = cv2.waitKey(1)
if k==27:
x,y,w,h = cv2.selectROI('cam',im)
cx,cy = (x+w/2,y+h/2)
break
target_pos, target_sz = np.array([cx, cy]), np.array([w, h])
state = SiamRPN_init(im, target_pos, target_sz, net) # init tracker
while True:
success,im=cap.read() # HxWxC
if success is not True:
break
state = SiamRPN_track(state, im) # track
bbox = np.array([state['target_pos'][0]-state['target_sz'][0]/2,
state['target_pos'][1]-state['target_sz'][1]/2,
state['target_pos'][0]+state['target_sz'][0]/2,
state['target_pos'][1]+state['target_sz'][1]/2]).astype(int)
pt = (state['target_pos'],state['target_sz'])
im_bbox = cv2.rectangle(im,(bbox[0],bbox[1]),(bbox[2],bbox[3]),(0,255,0),3)
cv2.imshow('cam',im_bbox)
k = cv2.waitKey(1)
if k==27:
cap.release()
cv2.destroyAllWindows()
break
import vot
from vot import Rectangle
import sys
import cv2 # imread
import torch
import numpy as np
from os.path import realpath, dirname, join
from net import SiamRPNBIG
from run_SiamRPN import SiamRPN_init, SiamRPN_track
from utils import get_axis_aligned_bbox, cxy_wh_2_rect
# load net
net_file = join(realpath(dirname(__file__)), 'SiamRPNBIG.model')
net = SiamRPNBIG()
net.load_state_dict(torch.load(net_file))
net.eval().cuda()
# warm up
for i in range(10):
net.temple(torch.autograd.Variable(torch.FloatTensor(1, 3, 127, 127)).cuda())
net(torch.autograd.Variable(torch.FloatTensor(1, 3, 255, 255)).cuda())
# start to track
handle = vot.VOT("polygon")
Polygon = handle.region()
cx, cy, w, h = get_axis_aligned_bbox(Polygon)
image_file = handle.frame()
if not image_file:
inter_rect_y2 = torch.min(b1_y2, b2_y2)
# Intersection area
inter_area = torch.clamp(inter_rect_x2 - inter_rect_x1 + 1, min=0) * \
torch.clamp(inter_rect_y2 - inter_rect_y1 + 1, min=0)
# Union Area
b1_area = (b1_x2 - b1_x1 + 1) * (b1_y2 - b1_y1 + 1)
b2_area = (b2_x2 - b2_x1 + 1) * (b2_y2 - b2_y1 + 1)
iou = inter_area / (b1_area + b2_area - inter_area + 1e-16)
return iou
# load net
net_file = join(realpath(dirname(__file__)), 'SiamRPNBIG.model')
net = SiamRPNBIG()
net.train()
config = TRAINING_PARAMS
optimizer = _get_optimizer(config, net)
net = net.cuda()
net.load_state_dict(torch.load(net_file))
lr_scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer,
T_max=15,
eta_min=1e-6)
# warm up
for i in range(10):
net.temple(
# print(data2[1])
data4=[]
for k in data2:
data3=np.array([0.0 if y=='' else float(y) for y in k])
data4.append(data3)
data_rect=np.array(data4)
# print(data_rect[0][0])
x1=data_rect[0][0]
y1=data_rect[0][1]
x2=data_rect[0][2]
y2=data_rect[0][3]
x3=data_rect[0][4]
y3=data_rect[0][5]
x4=data_rect[0][6]
y4=data_rect[0][7]
net = SiamRPNBIG()
net.load_state_dict(torch.load('/home/mars/Documents/Subject2018/vot2018-SiamRPN/DaSiamRPN-master/code/SiamRPNBIG.model'))
net.eval().cuda()
for i in range(10):
net.temple(torch.autograd.Variable(torch.FloatTensor(1, 3, 127, 127)).cuda())
net(torch.autograd.Variable(torch.FloatTensor(1, 3, 255, 255)).cuda())
cx = (x1+x2+x3+x4)/4
cy = (y1+y2+y3+y4)/4
w = ((x2-x1)+(x3-x4))/2
h = ((y3-y2)+(y4-y1))/2
target_pos, target_sz = np.array([cx, cy]), np.array([w, h])
image_file =image_path + img_name[0]
if __name__ == '__main__':
args = parse_args()
gpu_id = args.gpu_id
if gpu_id is None:
DEVICE = torch.device(f'cpu')
else:
DEVICE = torch.device(f'cuda:{gpu_id}')
z_size = (127, 127)
x_size = (255, 255)
batch_size = num_domains = 5
num_epoches = 100
loader = dataset.load_data(batch_size, z_size, x_size)['train']
net = SiamRPNBIG()
net.train().to(DEVICE)
# load_pretrained_weights(net, "./SiamRPNBIG.model")
optimizer = torch.optim.Adam(net.parameters(), weight_decay=0.001, lr=0.001)
for i_ep in range(num_epoches):
for i_iter, sample in enumerate(loader):
zs = sample['template'].to(DEVICE)
xs = sample['search_region'].to(DEVICE)
gt_boxes = sample['gt_box'] # .to(DEVICE)
optimizer.zero_grad()
net.temple(zs)
reg_output, cls_output = net.forward(xs) # of shape (50, 4*5, 17, 17), (50, 2*5, 17, 17)
feat_h, feat_w = cls_output.size(-2), cls_output.size(-1)
inter_rect_y2 = torch.min(b1_y2, b2_y2)
# Intersection area
inter_area = torch.clamp(inter_rect_x2 - inter_rect_x1 + 1, min=0) * \
torch.clamp(inter_rect_y2 - inter_rect_y1 + 1, min=0)
# Union Area
b1_area = (b1_x2 - b1_x1 + 1) * (b1_y2 - b1_y1 + 1)
b2_area = (b2_x2 - b2_x1 + 1) * (b2_y2 - b2_y1 + 1)
iou = inter_area / (b1_area + b2_area - inter_area + 1e-16)
return iou
# load net
net_file = join(realpath(dirname(__file__)), 'SiamRPNBIG.model')
net = SiamRPNBIG()
net.train()
config = TRAINING_PARAMS
optimizer = _get_optimizer(config, net)
net = net.cuda()
net.load_state_dict(torch.load(net_file))
lr_scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer,
T_max=15,
eta_min=1e-6)
# warm up
for i in range(10):
net.temple(
import vot
from vot import Rectangle
import sys
import cv2 # imread
import torch
import numpy as np
from os.path import realpath, dirname, join
from net import SiamRPNBIG
from run_SiamRPN import SiamRPN_init, SiamRPN_track
from utils import get_axis_aligned_bbox, cxy_wh_2_rect
# load net
net_file = join(realpath(dirname(__file__)), 'SiamRPNBIG.model')
net = SiamRPNBIG()
net.load_state_dict(torch.load(net_file, map_location="cpu"))
# net.eval().cpu()
net.eval().cpu()
# warm up
for i in range(10):
net.temple(torch.autograd.Variable(torch.FloatTensor(1, 3, 127, 127)).cpu())
net(torch.autograd.Variable(torch.FloatTensor(1, 3, 255, 255)).cpu())
# start to track
handle = vot.VOT("polygon")
Polygon = handle.region()
cx, cy, w, h = get_axis_aligned_bbox(Polygon)
image_file = handle.frame()
def loadNet():
net = SiamRPNBIG()
net.load_state_dict(
torch.load('/home/zhenglong/DaSiamRPN/code/SiamRPNBIG.model'))
net.eval().cuda()
return net
import vot
from vot import Rectangle
import sys
import cv2 # imread
import torch
import numpy as np
from os.path import realpath, dirname, join
from net import SiamRPNBIG
from run_SiamRPN import SiamRPN_init, SiamRPN_track
from utils import get_axis_aligned_bbox, cxy_wh_2_rect
# load net
net_file = join(realpath(dirname(__file__)), 'SiamRPNBIG.model')
net = SiamRPNBIG()
net.load_state_dict(torch.load(net_file)) # 加载模型参数
net.eval().cuda() # 对模型进行验证，cuda(device=None) 将所有模型参数和缓冲区移动到GPU
# warm up
# 预热，运行模板和检测分支10次，先屏蔽掉
# for i in range(10):
# net.temple(torch.autograd.Variable(torch.FloatTensor(1, 3, 127, 127)).cuda()) # selonsy:cuda()表示使用GPU进行计算,FloatTensor(1, 3, 127, 127)：浮点型四维张量
# net(torch.autograd.Variable(torch.FloatTensor(1, 3, 255, 255)).cuda())
# start to track
handle = vot.VOT("polygon")
Polygon = handle.region() # region：将配置消息发送到客户端并接收初始化区域和第一个图像的路径。其返回值为初始化区域。
cx, cy, w, h = get_axis_aligned_bbox(Polygon) # get_axis_aligned_bbox：将坐标数据转换成 RPN 的格式
image_file = handle.frame() # frame 函数从客户端获取帧（图像路径）
