Fix batch-wise inference #98
Merged
Conversation
This file contains hidden or 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
Suppress all but the top_k most confident predictions. Formerly only the least confident `top_k` were filtered out in the final "detect" step.
Contributor
Author
|
Part of this is redundant to an earlier PR I just noticed. |
Owner
|
Thanks for doing this. Sorry it took so long to get around to reviewing it. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Allows for deriving predictions of multiple images at a time in "test"-mode.
This can be tested in the
demo-notebook when stacking multiple input tensors, e.g. replacingxx = Variable(x.unsqueeze(0))byxx = Variable(torch.stack(input_tensors))whereinput_tensorsis a list of preprocessed images.