def preprocess_sample(self, x: TensorList) -> TensorList:
x *= self.window
sample_xf = fourier.cfft2(x)
return TensorList([
dcf.interpolate_dft(xf, bf)
for xf, bf in zip(sample_xf, self.interp_fs)
])
def localize_target(self, scores_raw):
if self.params.score_fusion_strategy == 'weightedsum':
weight = self.fparams.attribute('translation_weight')
scores_raw = weight * scores_raw
sf_weighted = fourier.cfft2(scores_raw) / (scores_raw.size(2) *
scores_raw.size(3))
for i, (sz,
ksz) in enumerate(zip(self.feature_sz, self.kernel_size)):
sf_weighted[i] = fourier.shift_fs(
sf_weighted[i],
math.pi *
(1 - torch.Tensor([ksz[0] % 2, ksz[1] % 2]) / sz))
scores_fs = fourier.sum_fs(sf_weighted)
scores = fourier.sample_fs(scores_fs, self.output_sz)
elif self.params.score_fusion_strategy == 'default':
if len(scores_raw) > 1:
raise NotImplementedError('Not implemented')
scores = scores_raw[0]
ksz = self.kernel_size[0]
offset = torch.Tensor([ksz[0] % 2, ksz[1] % 2]) / 2
else:
raise ValueError('Unknown score fusion strategy.')
if self.output_window is not None and not getattr(
self.params, 'perform_hn_without_windowing', False):
raise NotImplementedError
scores *= self.output_window
if getattr(self.params, 'advanced_localization', False):
return self.localize_advanced(scores)
# Get maximum
max_score, max_disp = dcf.max2d(scores)
_, scale_ind = torch.max(max_score, dim=0)
max_disp = max_disp.float().cpu()
# Convert to displacements in the base scale
if self.params.score_fusion_strategy == 'default':
disp = max_disp + offset
else:
disp = (max_disp +
self.output_sz / 2) % self.output_sz - self.output_sz / 2
# Compute translation vector and scale change factor
translation_vec = disp[scale_ind, ...].view(-1) * (
self.img_support_sz / self.output_sz) * self.target_scale
translation_vec *= self.params.scale_factors[scale_ind]
# Shift the score output for visualization purposes
if self.params.debug >= 2:
sz = scores.shape[-2:]
scores = torch.cat(
[scores[..., sz[0] // 2:, :], scores[..., :sz[0] // 2, :]], -2)
scores = torch.cat(
[scores[..., :, sz[1] // 2:], scores[..., :, :sz[1] // 2]], -1)
return translation_vec, scale_ind, scores, None
def localize_target(self, scores_raw):
# Weighted sum (if multiple features) with interpolation in fourier domain
weight = self.fparams.attribute('translation_weight',
1.0) #weight 没什么用
if (Debug):
print("weight : ", weight) #
scores_raw = weight * scores_raw #
if (Debug):
print("scores_raw: ", scores_raw)
sf_weighted = fourier.cfft2(scores_raw) / (scores_raw.size(2) *
scores_raw.size(3))
for i, (sz, ksz) in enumerate(zip(self.feature_sz, self.kernel_size)):
# """Shift a sample a in the Fourier domain.
sf_weighted[i] = fourier.shift_fs(
sf_weighted[i],
math.pi * (1 - torch.Tensor([ksz[0] % 2, ksz[1] % 2]) / sz))
#"""Sum a list of Fourier series expansions."""
scores_fs = fourier.sum_fs(sf_weighted)
if (Debug):
print("scores_fs : ", scores_fs)
#"""Samples the Fourier series."""
scores = fourier.sample_fs(scores_fs, self.output_sz)
if (Debug):
print("scores: ", scores)
if self.output_window is not None and not getattr(
self.params, 'perform_hn_without_windowing', False):
scores *= self.output_window
if getattr(self.params, 'advanced_localization', False):
if (Debug):
print("advanced: ")
return self.localize_advanced(scores)
# Get maximum
max_score, max_disp = dcf.max2d(scores)
_, scale_ind = torch.max(max_score, dim=0)
max_disp = max_disp.float().cpu()
# Convert to displacements in the base scale
disp = (max_disp +
self.output_sz / 2) % self.output_sz - self.output_sz / 2
# Compute translation vector and scale change factor
translation_vec = disp[scale_ind, ...].view(-1) * (
self.img_support_sz / self.output_sz) * self.target_scale
translation_vec *= self.params.scale_factors[scale_ind]
# Shift the score output for visualization purposes
if self.params.debug >= 2:
sz = scores.shape[-2:]
scores = torch.cat(
[scores[..., sz[0] // 2:, :], scores[..., :sz[0] // 2, :]], -2)
scores = torch.cat(
[scores[..., :, sz[1] // 2:], scores[..., :, :sz[1] // 2]], -1)
return translation_vec, scale_ind, scores, None
