def test_transform_siamfc(self):
base_dataset = VOT(self.vot_dir, return_rect=True, download=True)
transform = TransformSiamFC(stats_path=self.stats_path)
dataset = Pairwise(base_dataset, transform=transform, subset='train')
self.assertGreater(len(dataset), 0)
for crop_z, crop_x, labels, weights in dataset:
self.assertAlmostEqual(weights[labels == 1].sum().item(),
weights[labels == 0].sum().item())
self.assertAlmostEqual(weights.sum().item(),
labels[labels >= 0].numel())
self.assertEqual(
weights[labels == transform.ignore_label].sum().item(), 0)
if self.visualize:
crop_z, crop_x, labels, weights = random.choice(dataset)
crop_z = F.to_pil_image(crop_z / 255.0)
crop_x = F.to_pil_image(crop_x / 255.0)
labels = self._rescale(labels.cpu().squeeze().numpy())
weights = self._rescale(weights.cpu().squeeze().numpy())
bndbox_z = np.array([31, 31, 64, 64])
bndbox_x = np.array([95, 95, 64, 64])
show_frame(crop_z, bndbox_z, fig_n=1, pause=1)
show_frame(crop_x, bndbox_x, fig_n=2, pause=1)
show_frame(labels, fig_n=3, pause=1, cmap='hot')
show_frame(weights, fig_n=4, pause=5, cmap='hot')
def test_transform_goturn(self):
base_dataset = VOT(self.vot_dir, return_rect=True, download=True)
transform = TransformGOTURN()
dataset = Pairwise(base_dataset,
transform,
pairs_per_video=1,
frame_range=1,
causal=True)
self.assertGreater(len(dataset), 0)
for crop_z, crop_x, labels in dataset:
self.assertEqual(crop_z.size(), crop_x.size())
if self.visualize:
for t in range(10):
crop_z, crop_x, labels = random.choice(dataset)
mean_color = torch.tensor(transform.mean_color).float().view(
3, 1, 1)
crop_z = F.to_pil_image((crop_z + mean_color) / 255.0)
crop_x = F.to_pil_image((crop_x + mean_color) / 255.0)
labels = labels.cpu().numpy()
labels *= transform.out_size / transform.label_scale_factor
bndbox = np.concatenate([labels[:2], labels[2:] - labels[:2]])
show_frame(crop_x, bndbox, fig_n=1, pause=1)
def test_goturn_track(self):
dataset = VOT(self.vot_dir, return_rect=True, download=True)
tracker = TrackerGOTURN(self.net_path)
img_files, anno = random.choice(dataset)
rects, speed = tracker.track(img_files, anno[0, :],
visualize=True)
self.assertEqual(rects.shape, anno.shape)
def test_siamfc_track_v2(self):
dataset = VOT(self.vot_dir, return_rect=True, download=True)
tracker = TrackerSiamFC(
branch='alexv2', net_path=self.net_v2, z_lr=0.01,
response_up=8, scale_step=1.0816, window_influence=0.25)
img_files, anno = random.choice(dataset)
rects, speed = tracker.track(img_files, anno[0, :],
visualize=True)
self.assertEqual(rects.shape, anno.shape)
def test_load(self):
dataset = VOT(self.vot_dir, return_rect=True)
self.assertGreater(len(dataset), 0)
for img_files, anno in dataset:
self.assertGreater(len(img_files), 0)
self.assertEqual(len(img_files), len(anno))
if self.visualize:
img_files, anno = random.choice(dataset)
for f, img_file in enumerate(img_files):
image = Image.open(img_file)
show_frame(image, anno[f, :])
def test_goturn_train(self):
tracker = TrackerGOTURN(net_path=self.net_path)
transform = TransformGOTURN()
base_dataset = VOT(self.vot_dir, return_rect=True, download=True)
dataset = Pairwise(
base_dataset, transform, frame_range=1, causal=True)
dataloader = DataLoader(dataset, batch_size=2, shuffle=True)
# training loop
for it, batch in enumerate(dataloader):
update_lr = it == 0
loss = tracker.step(batch, backward=True, update_lr=update_lr)
print('Iter: {} Loss: {:.6f}'.format(it + 1, loss))
# validation loop
for it, batch in enumerate(dataloader):
loss = tracker.step(batch, backward=False)
print('Val. Iter: {} Loss: {:.6f}'.format(it + 1, loss))
def test_siamfc_train_v2(self):
tracker = TrackerSiamFC(branch='alexv2')
transform = TransformSiamFC(
stats_path=self.stats_path, score_sz=33,
r_pos=8, total_stride=4)
base_dataset = VOT(self.vot_dir, return_rect=True, download=True)
dataset = Pairwise(base_dataset, transform, pairs_per_video=1)
dataloader = DataLoader(dataset, batch_size=2, shuffle=True)
# training loop
for it, batch in enumerate(dataloader):
update_lr = it == 0
loss = tracker.step(batch, backward=True, update_lr=update_lr)
print('Iter: {} Loss: {:.6f}'.format(it + 1, loss))
# val loop
for it, batch in enumerate(dataloader):
loss = tracker.step(batch, backward=False)
print('Val. Iter: {} Loss: {:.6f}'.format(it + 1, loss))
def test_download(self):
dataset = VOT(self.vot_dir, download=True, version=2017)
self.assertGreater(len(dataset), 0)
def test_experiment_unsupervised(self):
experiment = ExperimentUnsupervised(log_dir='results/SiamFC')
tracker = TrackerSiamFC(net_path=self.net_path)
dataset = VOT(self.vot_dir, return_rect=True)
experiment.run(tracker, dataset, visualize=True)