Skip to content

Conversation

@justinpinkney
Copy link
Collaborator

To implement feature #5 we make the image type and range conversion more
streamlined. Images are now converted to the expected type and range
(single -1 to 1) as the first step in detection. This gives some changes
in the numerics due to differences in types for pre-processing steps.

justinpinkney and others added 2 commits March 31, 2020 12:08
To implement feature #5 we make the image type and range conversion more
streamlined. Images are now converted to the expected type and range
(single -1 to 1) as the first step in detection. This gives some changes
in the numerics due to differences in types for pre-processing steps.
@justinpinkney justinpinkney merged commit c5086ea into master Mar 31, 2020
@justinpinkney justinpinkney deleted the feature/5 branch March 31, 2020 12:21
@justinpinkney justinpinkney linked an issue Mar 31, 2020 that may be closed by this pull request
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Accept float images in range 0-1

2 participants