Patch size can now be defined in the settings #1
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
…not optimizing anymore
…fferently to hopefully keep gradient
…and transfered function inside patch_placement
… is NOT 'nearest'
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Outdated suggestions cannot be applied.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.
Replaced PyTorch's affine_grid(.) function by a slightly adapted implementation of perspective_grid(.) to deal with variable patch sizes.
Since the patches are now placed in the images starting from the top left corner instead of the center, the ranges for the values of the transformation matrices had to be adjusted.
Similarly, since this method now allows for the translation vector to be in the range of the dimensions of the whole camera image instead of expecting them to be normalized between [-1, 1], the standard deviation of the noise added to them inside gen_noisy_transformations(.) had to be increased.