def init(self, im, target_pos, target_sz, model, hp=None):
state = dict()
state['im_h'] = im.shape[0]
state['im_w'] = im.shape[1]
p = RPNConfig()
# single test
if not hp and not self.info.epoch_test:
prefix = [x for x in ['OTB', 'VOT'] if x in self.info.dataset]
cfg = load_yaml('./experiments/test/{0}/{1}.yaml'.format(
prefix[0], self.info.arch))
cfg_benchmark = cfg[self.info.dataset]
p.update(cfg_benchmark)
p.renew()
# for vot17 or vot18: from siamrpn released
if '2017' in self.info.dataset:
if ((target_sz[0] * target_sz[1]) /
float(state['im_h'] * state['im_w'])) < 0.004:
p.instance_size = 287
p.renew()
else:
p.instance_size = 271
p.renew()
net = model
p.anchor = generate_anchor(p.total_stride, p.scales, p.ratios,
p.score_size)
avg_chans = np.mean(im, axis=(0, 1))
wc_z = target_sz[0] + p.context_amount * sum(target_sz)
hc_z = target_sz[1] + p.context_amount * sum(target_sz)
s_z = python2round(np.sqrt(wc_z * hc_z))
z_crop = get_subwindow_tracking(im, target_pos, p.exemplar_size, s_z,
avg_chans)
z = Variable(z_crop.unsqueeze(0))
net.template(z.cuda())
if p.windowing == 'cosine':
window = np.outer(np.hanning(p.score_size),
np.hanning(p.score_size)) # [17,17]
elif p.windowing == 'uniform':
window = np.ones((p.score_size, p.score_size))
window = np.expand_dims(window, axis=0) # [1,17,17]
window = np.repeat(window, p.anchor_num, axis=0) # [5,17,17]
state['p'] = p
state['net'] = net
state['avg_chans'] = avg_chans
state['window'] = window
state['target_pos'] = target_pos
state['target_sz'] = target_sz
return state
def init(self, im, target_pos, target_sz, model, hp=None):
self.frame_num = 1
self.temp_max = 0
self.lost_count = 0
state = dict()
state['im_h'] = im.shape[0]
state['im_w'] = im.shape[1]
p = RPNConfig()
# single test
if not hp and not self.info.epoch_test:
prefix = [x for x in ['OTB', 'VOT'] if x in self.info.dataset]
cfg_ = load_yaml('../experiments/test/{0}/{1}.yaml'.format(prefix[0], self.info.arch))
cfg_benchmark = cfg_[self.info.dataset]
p.update(cfg_benchmark)
p.renew()
# for vot17 or vot18: from siamrpn released
if '2017' in self.info.dataset:
if ((target_sz[0] * target_sz[1]) / float(state['im_h'] * state['im_w'])) < 0.004:
p.instance_size = 287
p.renew()
else:
p.instance_size = 271
p.renew()
# param tune
if hp:
p.update(hp)
p.renew()
# for small object (from DaSiamRPN released)
if ((target_sz[0] * target_sz[1]) / float(state['im_h'] * state['im_w'])) < 0.004:
p.instance_size = hp['big_sz']
p.renew()
else:
p.instance_size = hp['small_sz']
p.renew()
net = model
p.anchor = generate_anchor(p.total_stride, p.scales, p.ratios, p.score_size)
avg_chans = np.mean(im, axis=(0, 1))
wc_z = target_sz[0] + p.context_amount * sum(target_sz)
hc_z = target_sz[1] + p.context_amount * sum(target_sz)
s_z = python2round(np.sqrt(wc_z * hc_z))
z_crop = get_subwindow_tracking(im, target_pos, p.exemplar_size, s_z, avg_chans)
z = Variable(z_crop.unsqueeze(0))
net.template(z.cuda())
if p.windowing == 'cosine':
window = np.outer(np.hanning(p.score_size), np.hanning(p.score_size)) # [17,17]
elif p.windowing == 'uniform':
window = np.ones((p.score_size, p.score_size))
window = np.expand_dims(window, axis=0) # [1,17,17]
window = np.repeat(window, p.anchor_num, axis=0) # [5,17,17]
if cfg.TRACK.USE_CLASSIFIER:
# atom = ATOM().cuda().eval()
# checkpoint_dict = torch.load("/home/zhuyi/Code/CRPN_511/atom_pretrain.pth")
# atom.load_state_dict(checkpoint_dict["net"],strict=False)
self.classifier = BaseClassifier(net)
self.center_pos = np.array(target_pos)
self.size = np.array(target_sz)
bbox = [target_pos[0]-(target_sz[0]-1)/2,target_pos[1]-(target_sz[1]-1)/2,target_sz[0],target_sz[1]]
#bbox = [cx - (w - 1) / 2, cy - (h - 1) / 2, w, h]
if cfg.TRACK.TEMPLATE_UPDATE:
with torch.no_grad():
net.template_short_term(self.z_crop)
s_xx = s_z * (cfg.TRACK.INSTANCE_SIZE * 2 / cfg.TRACK.EXEMPLAR_SIZE)
x_crop = get_subwindow_tracking(im, self.center_pos, cfg.TRACK.INSTANCE_SIZE * 2,
round(s_xx), avg_chans)
x_crop =x_crop.unsqueeze(0)
self.classifier.initialize(x_crop.type(torch.FloatTensor), bbox)
state['p'] = p
state['net'] = net
state['avg_chans'] = avg_chans
state['window'] = window
state['target_pos'] = target_pos
state['target_sz'] = target_sz
return state