Adding cast to fp32 for TensorRT no image case #3917
Merged
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
|
Also, realized this was not in CODEOWNERS. Adding. |
omegafragger
pushed a commit
to omegafragger/models
that referenced
this pull request
May 15, 2018
* Adding cast to fp32 * Adding myself to OWNERS
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Outdated suggestions cannot be applied.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.
Numpy defaults to creating fp64, which causes TF/tensorRT to reject the random data. This fixes that.
Just for fun-- what does random data look like to the classifier? This particular bit of randomness came out as:
Precision: native [u'nematode, nematode worm, roundworm', u'panpipe, pandean pipe, syrinx', u'revolver, six-gun, six-shooter', u'bolo tie, bolo, bola tie, bola', u'hatchet']