Open xmfcx opened 1 year ago
The ARM64 network repository https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/sbsa/ still doesn't have tensorrt-dev
available.
I think we should also wait until this is available too.
Because the new code is not backwards compatible.
(Update on 2022-12-21: I've updated them to be backwards compatible.)
We could also install old packages to ARM64
and new packages to x86_64
too but it would make things complicated.
What do you think, @wep21 @kenji-miyake ?
I think we should also wait until this is available too.
:+1: Using different versions for arm64 and amd64 would be too complicated.
Nice!
Doesn't lidar_apollo_instance_segmentation
need to be updated?
@yukke42
Doesn't
lidar_apollo_instance_segmentation
need to be updated?
With all current PRs applied, everything compiled fine. I also checked lidar_apollo_instance_segmentation/lib/src/TrtNet.cpp and it doesn't look like it's using outdated APIs similar to ones I've changed.
Tomorrow I will try to compile it again just to be sure.
traffic_light_classifier
fix was small, it is merged with https://github.com/autowarefoundation/autoware.universe/pull/2325 to support both versions.enqueueV2
to enqueueV3
and updated versions doesn't work.tensorrt_yolox
package was added.
cc @wep21 @kenji-miyake @yukkysaito
As for guidance in understanding the the enqueueV2
to enqueueV3
transition, following resources can be helpful:
enqueueV3
is used.v2
to v3
(search for sampleInference and expand) https://github.com/NVIDIA/TensorRT/commit/1d6bf36034bb07fc88d924ebf5d34d358298e545#diff-aae446aa5c914afd563008477f89fafa3cb0f9b58fb4d23b8aeeafb2ba4c693bAlso from my experience on the task:
v2
so I removed them, I think they should be used somehow.
bool setTensorAddress(char const* tensorName, void* data) noexcept
must be used for this but I couldn't figure how.This pull request has been automatically marked as stale because it has not had recent activity.
Checklist
Description
Currently in CI for humble & Ubuntu 22.04, we are using old (Ubuntu 20.04) packages for TensorRT.
In the latest (currently
tensorrt-dev_8.5.1.7-1+cuda11.8
) TensorRT version, some old APIs are deprecated.Purpose
This issue is created to track upgrading the following 4 packages to compile and run Autoware Universe successfully.
Possible approaches
galactic
traffic_light_classifier
https://github.com/autowarefoundation/autoware.universe/pull/2325traffic_light_ssd_fine_detector
https://github.com/autowarefoundation/autoware.universe/pull/2326tensorrt_yolo
https://github.com/autowarefoundation/autoware.universe/pull/2327lidar_centerpoint
https://github.com/autowarefoundation/autoware.universe/pull/2328tensorrt_yolox
(no PR created)Definition of done
traffic_light_classifier
works normallytraffic_light_ssd_fine_detector
works normallytensorrt_yolo
works normallylidar_centerpoint
works normallytensorrt_yolox
works normally