Retina broken log polar WIP #721
Open
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
depends on params sparsityXXX > 0
instead of doing it manually
replace self.output_diameter with self.retina.getOutputSize() replace self.retina_diameter with self.retina.getInputSize()
require same dims for all images make new_image_() a static method, used internally by compute()
TODO avoid that, work with rectangles?
processing.
This reverts commit 40dd4b30781c96f8b5bae9545f258c73e75592ce.
This reverts commit e46d5f3.
breznak
commented
Oct 22, 2019
There was a problem hiding this comment.
CC @ctrl-z-9000-times please have a look at these, and esp the issues in this PR's description, thank you.
| self.resolution_factor = 3 | ||
| self.retina_diameter = int(self.resolution_factor * output_diameter) | ||
| # Argument fovea_scale ... represents "zoom" aka distance from the object/image. | ||
| self.fovea_scale = 0.177 |
There was a problem hiding this comment.
fovea_scale vs self.scale?
| self.scale = 1.0 | ||
|
|
||
|
|
||
| def new_image_(image): |
There was a problem hiding this comment.
now static, rename to read_image?
| center = self.retina_diameter / 2 | ||
| M = self.retina_diameter * self.fovea_scale | ||
| center = self.retina.getInputSize()[0] / 2 | ||
| M = self.retina.getInputSize()[0] * self.scale | ||
| if self.parvo_enc is not None: | ||
| parvo = cv2.logPolar(parvo, |
There was a problem hiding this comment.
should we apply the logPolar only in the Channel encoder? Bcs that one expects its data in that form.
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Outdated suggestions cannot be applied.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.
WIP PR, I made some cleanups,improvements to the PR, but broke scaling/logpolar.
What I'd like to do is use Retina's
useLogSampling, but imho that unfortunatelyOur current approach is neither ideal,
we have to crop to ROI
I'd like to re-center the image to given center (& fov. diameter)
What is the difference for
self.scaleandself.scale_fovea?Follow up to #691