Optimize endoscopy tool tracking app #550
Open
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
AndreasHeumann
force-pushed
the
ah/opt_endoscopy_tool_tracking
branch
2 times, most recently
from
571f03f
to
92ca191
Compare
Modify ToolTrackingPostProcessorOp to generate coordinates using CUDA. This avoids the roundtrip from GPU to CPU memory and back. Use RMMAllocator for video replayer. Fix type of `dla_core` parameter of TensorRtInference. Remove unused `clock` parameter. Latency measured with flow benchmarking on x86 with RTX 6000 Ada and replayer `realtime`set to `false`: before optimizatio 4.8 ms, after optimization 3.09 ms. Signed-off-by: Andreas Heumann <[email protected]>
AndreasHeumann
force-pushed
the
ah/opt_endoscopy_tool_tracking
branch
from
92ca191
to
6f47228
Compare
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Outdated suggestions cannot be applied.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.
Optimize endoscopy tool tracking app
Modify ToolTrackingPostProcessorOp to generate coordinates using
CUDA. This avoids the roundtrip from GPU to CPU memory and back.
Use RMMAllocator for video replayer.
Fix type of
dla_coreparameter of TensorRtInference.Remove unused
clockparameter.Latency measured with flow benchmarking on x86 with RTX 6000 Ada
and replayer
realtimeset tofalse:before optimizatio 4.8 ms, after optimization 3.09 ms.