You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am reading the code ,but i do not know the meaning of the number 0.5
# self.num_learnable_pts = 2
if self.num_learnable_pts > 0 and instance_feature is not None:
# 为什么要-0.5
learnable_scale = (
safe_sigmoid(self.learnable_fc(instance_feature)
.reshape(bs, num_anchor, self.num_learnable_pts, 3))
- 0.5
)
The text was updated successfully, but these errors were encountered:
We sample reference points around the anchor xyz, so -0.5 accounts for those that fall on the negative halves of the axes given the sigmoid function yields values in the range of (0, 1).
We sample reference points around the anchor xyz, so -0.5 accounts for those that fall on the negative halves of the axes given the sigmoid function yields values in the range of (0, 1).
I am reading the code ,but i do not know the meaning of the number 0.5
# self.num_learnable_pts = 2
if self.num_learnable_pts > 0 and instance_feature is not None:
# 为什么要-0.5
learnable_scale = (
safe_sigmoid(self.learnable_fc(instance_feature)
.reshape(bs, num_anchor, self.num_learnable_pts, 3))
- 0.5
)
The text was updated successfully, but these errors were encountered: