def forward(self, input):
"""
Forward pass of the function.
"""
return (
(input > 2).float()
+ (input - F.pow(input, 2) / 4)
* (input >= 0).float()
* (input <= 2).float()
+ (input + F.pow(input, 2) / 4)
* (input < 0).float()
* (input >= -2).float()
- (input < -2).float()
)
def _abs_robust(diff, occ_mask=None, if_mask_=False):
loss_diff = F.pow((F.abs(diff) + 0.01), 0.4)
if not if_mask_:
photo_loss = F.mean(loss_diff)
else:
photo_loss = F.sum(loss_diff * occ_mask) / (F.sum(occ_mask) + 1e-6)
return photo_loss
def _charbonnier(diff, occ_mask=None, if_mask_=False):
loss_diff = F.pow((diff**2 + 1e-6), 0.4)
if not if_mask_:
photo_loss = F.mean(loss_diff)
else:
photo_loss = F.sum(loss_diff * occ_mask) / (F.sum(occ_mask) + 1e-6)
return photo_loss
def test_BetaRNG():
m1 = RNG(seed=111, device="xpu0")
m2 = RNG(seed=111, device="xpu1")
m3 = RNG(seed=222, device="xpu0")
out1 = m1.beta(2, 1, size=(100, ))
out1_ = m1.uniform(size=(100, ))
out2 = m2.beta(2, 1, size=(100, ))
out3 = m3.beta(2, 1, size=(100, ))
np.testing.assert_allclose(out1.numpy(), out2.numpy(), atol=1e-6)
assert out1.device == "xpu0" and out2.device == "xpu1"
assert not (out1.numpy() == out3.numpy()).all()
assert not (out1.numpy() == out1_.numpy()).all()
alpha = Tensor([[2, 3, 4], [9, 10, 11]], dtype=np.float32, device="xpu0")
beta = Tensor([0.5, 1, 1.5], dtype=np.float32, device="xpu0")
expected_mean = (alpha / (alpha + beta)).numpy()
expected_std = (F.sqrt(alpha * beta / (F.pow(alpha + beta, 2) *
(alpha + beta + 1)))).numpy()
out = m1.beta(alpha=alpha, beta=beta, size=(20, 30))
out_shp = out.shape
if isinstance(out_shp, tuple):
assert out_shp == (20, 30, 2, 3)
else:
assert all(out.shape.numpy() == np.array([20, 30, 2, 3]))
assert (np.abs(out.mean(axis=(0, 1)).numpy() - expected_mean) /
expected_std).mean() < 0.1
assert (np.abs(np.std(out.numpy(), axis=(0, 1)) -
expected_std)).mean() < 0.1
def forward(self, x):
B, C, _, _ = x.shape
# avg_dims = tuple(range(2, len(x.shape))) # [2 ,3 ]
nu2 = F.expand_dims(F.pow(x, 2).reshape(B, C, -1).mean(axis=-1,
keepdims=True),
axis=-1) # [B, C, 1, 1]
x = x / F.sqrt(nu2 + F.abs(self.eps))
return F.maximum(self.gamma * x + self.beta, self.tau)
def SSIM(x, y, md=1):
patch_size = 2 * md + 1
C1 = 0.01**2
C2 = 0.03**2
mu_x = nn.AvgPool2d(patch_size, 1, 0, mode="average")(x)
mu_y = nn.AvgPool2d(patch_size, 1, 0, mode="average")(y)
mu_x_mu_y = mu_x * mu_y
mu_x_sq = F.pow(mu_x, 2)
mu_y_sq = F.pow(mu_y, 2)
sigma_x = nn.AvgPool2d(patch_size, 1, 0, mode="average")(x * x) - mu_x_sq
sigma_y = nn.AvgPool2d(patch_size, 1, 0, mode="average")(y * y) - mu_y_sq
sigma_xy = nn.AvgPool2d(patch_size, 1, 0, mode="average")(
x * y) - mu_x_mu_y
SSIM_n = (2 * mu_x_mu_y + C1) * (2 * sigma_xy + C2)
SSIM_d = (mu_x_sq + mu_y_sq + C1) * (sigma_x + sigma_y + C2)
SSIM = SSIM_n / SSIM_d
dist = F.clip((1 - SSIM) / 2, 0, 1)
return dist
def sigmoid_cross_entropy_retina(pred,
label,
ignore_label=-1,
background=0,
alpha=0.5,
gamma=0):
device = pred.device
mask = 1 - F.equal(label, ignore_label).astype(np.float32)
vlabel = label * mask
n, m, c = pred.shape
zero_mat = F.zeros([n, m, c + 1]).to(device)
index = F.expand_dims(vlabel, 2).astype(np.int32)
one_hot = F.scatter(zero_mat, 2, index, F.ones([n, m, 1]))
onehot = one_hot[:, :, 1:]
pos_part = F.pow(1 - pred, gamma) * onehot * F.log(pred)
neg_part = F.pow(pred, gamma) * (1 - onehot) * F.log(1 - pred)
loss = -(alpha * pos_part + (1 - alpha) * neg_part).sum(axis=2) * mask
positive_mask = (label > 0)
return loss.sum() / F.maximum(positive_mask.sum(), 1)
def forward(self, input):
"""
Forward pass of the function.
"""
return F.pow((1 + F.exp(-self.beta * input)), -self.alpha)
def isru(input, alpha):
return input / (F.sqrt(1 + alpha * F.pow(input, 2)))
def _anchor_double_target(gt_boxes, im_info, all_anchors):
gt_boxes, im_info = gt_boxes.detach(), im_info.detach()
all_anchors = all_anchors.detach()
gt_boxes = gt_boxes[:im_info[5].astype(np.int32), :]
dummy = -F.ones([1, gt_boxes.shape[1]]).to(gt_boxes.device)
gt_boxes = F.concat([gt_boxes, dummy], axis=0)
valid_mask = 1 - (gt_boxes[:, 4] < 0).astype(np.float32)
anchor_centers = _compute_center(all_anchors)
gtboxes_centers = _compute_center(gt_boxes)
# gtboxes_centers = gtboxes_centers * valid_mask.unsqueeze(1)
gtboxes_centers = gtboxes_centers * F.expand_dims(valid_mask, axis=1)
N, K = all_anchors.shape[0], gt_boxes.shape[0]
an_centers = F.expand_dims(anchor_centers, axis=1)
gt_centers = F.expand_dims(gtboxes_centers, axis=0)
# an_centers = anchor_centers.unsqueeze(1).repeat(1, K, 1)
# gt_centers = gtboxes_centers.unsqueeze(0).repeat(N, 1, 1)
distance = F.abs(an_centers - gt_centers)
distance = F.sqrt(F.pow(distance, 2).sum(axis=2))
start = 0
end = 5
overlaps = box_overlap_opr(all_anchors[:, :4], gt_boxes[:, :4])
overlaps *= F.expand_dims(valid_mask, axis=0)
default_num = 16
ious_list = []
for l in range(start, end):
_, index = F.cond_take(all_anchors[:, 4] == l, all_anchors[:, 4])
level_dist = distance[index, :].transpose(1, 0)
ious = overlaps[index, :].transpose(1, 0)
sorted_index = F.argsort(level_dist, descending=False)
n = min(sorted_index.shape[1], default_num)
ious = F.gather(ious, 1, sorted_index[:, :n]).transpose(1, 0)
ious_list.append(ious)
ious = F.concat(ious_list, axis=0)
mean_var = F.mean(ious, axis=0)
std_var = F.std(ious, 0)
iou_thresh_per_gt = mean_var + std_var
iou_thresh_per_gt = F.maximum(iou_thresh_per_gt, 0.2)
# limits the anchor centers in the gtboxes
N, K = all_anchors.shape[0], gt_boxes.shape[0]
anchor_points = an_centers
pos_area = _compute_pos_area(gt_boxes, 0.3)
# pos_area = pos_area.unsqueeze(0).repeat(N, 1, 1)
pos_area = F.broadcast_to(F.expand_dims(pos_area, axis=0),
(N, K, pos_area.shape[-1]))
l = anchor_points[:, :, 0] - pos_area[:, :, 0]
r = pos_area[:, :, 2] - anchor_points[:, :, 0]
t = anchor_points[:, :, 1] - pos_area[:, :, 1]
b = pos_area[:, :, 3] - anchor_points[:, :, 1]
is_in_gt = F.stack([l, r, t, b], axis=2)
is_in_gt = is_in_gt.min(axis=2) > 0.1
valid_mask = (overlaps >= F.expand_dims(
iou_thresh_per_gt, axis=0)) * is_in_gt.astype(np.float32)
ious = overlaps * valid_mask
sorted_index = F.argsort(ious, 1)
sorted_overlaps = F.gather(ious, 1, sorted_index)
max_overlaps = sorted_overlaps[:, :2].flatten()
argmax_overlaps = sorted_index[:, :2].flatten()
n, c = all_anchors.shape
device = all_anchors.device
labels = -F.ones(2 * n).to(device)
positive_mask = (max_overlaps >= 0.2).to(device).astype(np.float32)
negative_mask = (max_overlaps < 0.2).to(device).astype(np.float32)
labels = positive_mask + labels * (1 - positive_mask) * (1 - negative_mask)
bbox_targets = gt_boxes[argmax_overlaps, :4]
all_anchors = F.broadcast_to(F.expand_dims(all_anchors, axis=1),
(n, 2, c)).reshape(-1, c)
bbox_targets = bbox_transform_opr(all_anchors[:, :4], bbox_targets)
labels_cat = gt_boxes[argmax_overlaps, 4]
labels_cat = labels_cat * (1 - F.equal(labels, -1).astype(
np.float32)) - F.equal(labels, -1).astype(np.float32)
return labels, bbox_targets, labels_cat
def _anchor_target(gt_boxes, im_info, all_anchors):
gt_boxes, im_info = gt_boxes.detach(), im_info.detach()
all_anchors = all_anchors.detach()
gt_boxes = gt_boxes[:im_info[5], :]
valid_mask = 1 - (gt_boxes[:, 4] < 0).astype(np.float32)
anchor_centers = _compute_center(all_anchors)
gtboxes_centers = _compute_center(gt_boxes) * F.expand_dims(valid_mask,
axis=0)
N, K = all_anchors.shape[0], gt_boxes.shape[0]
# an_centers = anchor_centers.unsqueeze(1).repeat(1, K, 1)
an_centers = F.expand_dims(anchor_centers, axis=1)
gt_centers = F.expand_dims(gtboxes_centers, axis=0)
# gt_centers = gtboxes_centers.unsqueeze(0).repeat(N, 1, 1)
distance = F.abs(an_centers - gt_centers)
distance = F.sqrt(F.pow(distance, 2).sum(axis=2))
start = 0
end = 5
overlaps = box_overlap_opr(all_anchors[:, :4], gt_boxes[:, :4])
overlaps = overlaps * valid_mask.unsqueeze(0)
default_num = 9
ious_list = []
for l in range(start, end):
index = torch.nonzero(all_anchors[:, 4].eq(l), as_tuple=False)[:, 0]
level_dist = level_dist[index, :].transpose(1, 0)
ious = distance[index, :].transpose(1, 0)
sorted_index = torch.argsort(ious, 1, descending=False)
n = min(default_num, sorted_index.shape[1])
ious = torch.gather(ious, 1, sorted_index[:, :n]).transpose(1, 0)
ious_list.append(ious)
ious = F.concat(ious_list, axis=0)
mean_var = ious.mean(0)
std_var = ious.std(0)
iou_thresh_per_gt = mean_var + std_var
iou_thresh_per_gt = torch.clamp(iou_thresh_per_gt, 0.35)
n = iou_thresh_per_gt.shape[0]
# limits the anchor centers in the gtboxes
N, K = all_anchors.shape[0], gt_boxes.shape[0]
anchor_points = an_centers
proxies = gt_boxes.unsqueeze(0).repeat(N, 1, 1)
l = anchor_points[:, :, 0] - proxies[:, :, 0]
r = proxies[:, :, 2] - anchor_points[:, :, 0]
t = anchor_points[:, :, 1] - proxies[:, :, 1]
b = proxies[:, :, 3] - anchor_points[:, :, 1]
is_in_gt = F.stack([l, r, t, b], axis=2)
is_in_gt = is_in_gt.min(axis=2) > 0.1
valid_mask = (overlaps >= iou_thresh_per_gt.unsqueeze(0)) * is_in_gt
ious = overlaps * valid_mask
argmax_overlaps = torch.argmax(ious, axis=1)
max_overlaps = torch.gather(ious, 1, argmax_overlaps.unsqueeze(1))
n = all_anchors.shape[0]
labels = -F.ones(n)
positive_mask = max_overlaps > 0
negative_mask = max_overlaps < config.rpn_negative_overlap
labels = positive_mask + labels * (1 - positive_mask) * (1 - negative_mask)
bbox_targets = gt_boxes[argmax_overlaps, :4]
bbox_targets = bbox_transform_opr(all_anchors[:, :4], bbox_targets)
labels_cat = gt_boxes[argmax_overlaps, 4]
labels_cat = labels_cat * (1 - labels.eq(0).astype(np.float32))
labels_cat = labels_cat * (1 - labels.eq(-1).astype(
np.float32)) - labels.eq(-1).astype(np.float32)
return labels, bbox_targets, labels_cat