Error in calculation of threshold of frustum. #65
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ns. This leads to better performance in rotation prediction.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There were parantheses missing to calculate the mean of min and max. Therefore the frustum was always too large. The expansion factor delta, which in the paper was argued to need to be greater than zero, is set to zero by default. The error in the frustum threshold calculation leads to this choice of delta making more sense.
Although this seems to be a straight hickup, we found that calculating it correctly worsens the performance even if we set the expansion factor to a value such that the frustum is approximately as big as before. The relationship of the frustum size and the network's performance needs to be investigated more. For now, this calculation is in our view an error and the frustum size should be controlled by the expansion factor instead.