Simplify inference with ONNX models #2060
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
This allows using the base DataConfig class instead of a specific subclass (e.g. like SemanticSegmentationGeoDataConfig) which makes it easier to define a Learner for inference. For instance, one can now simply define a learner for ONNX inference like so:
learner = SemanticSegmentationLearner(
cfg=SemanticSegmentationLearnerConfig(data=DataConfig(img_sz=512)),
model_weights_path='model.onnx',
training=False,
)
This decouples prediction from the PyTorchLearnerBackends.
AdeelH
changed the title
Codecov ReportAttention:
Additional details and impacted files@@ Coverage Diff @@
## master #2060 +/- ##
==========================================
- Coverage 89.75% 89.65% -0.11%
==========================================
Files 196 197 +1
Lines 9735 9761 +26
==========================================
+ Hits 8738 8751 +13
- Misses 997 1010 +13 ☔ View full report in Codecov by Sentry. |
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Outdated suggestions cannot be applied.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.
Overview
This PR makes it easier to use an ONNX model for inference. See commits for details.
Checklist
needs-backportlabel if the change should be back-ported to the previous releaseNotes
N/A
Testing Instructions