(wip) n-channel imagery and improved show funcs in show_batch, train loop, and show_results #90
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
…band somewhere. aug_transforms incompatible with new data block
rbavery
changed the title
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Outdated suggestions cannot be applied.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.
this pr is tabled due to issues with fastai assuming 3 channels
*no pretraining without norm result sin val loss and metric not changing, and all predictions being the same, with two pixels in lower right hand corner
These issues seem to stem from using a custom TensorImage class and discarding the use of PIL. This is the main difference between single channel CV1 and single channel CV2.