fix(lidar_apollo_segmentation_tvm, tvm_utility): fixed output dim and pipeline

[angry-crab]

Signed-off-by: Xinyu Wang xinyu.wang@tier4.jp

Description

Resolve #1988
Changed default allocation device according to config. Fixed output data transfer in case of GPU involved.
Reason discussed in the follwing issue.
#1898

Pre-review checklist for the PR author

The PR author must check the checkboxes below when creating the PR.

• I've confirmed the contribution guidelines.
• The PR follows the pull request guidelines.

In-review checklist for the PR reviewers

The PR reviewers must check the checkboxes below before approval.

• The PR follows the pull request guidelines.

Post-review checklist for the PR author

The PR author must check the checkboxes below before merging.

• There are no open discussions or they are tracked via tickets.

After all checkboxes are checked, anyone who has write access can merge the PR.

[angry-crab]

update bcnn has to be merged before this one.

[ambroise-arm]

With the update of the model, the unit test of lidar_apollo_segmentaiton_tvm doesn't pass anymore:

autoware.universe/perception/lidar_apollo_segmentation_tvm/test/main.cpp

Line 89 in 2997983

TEST(lidar_apollo_segmentation_tvm, runtime_error) { test_segmentation(false, false, true); }

Which needs to become test_segmentation(false, false, false).
The comments won't make much sense then. Maybe you could put the 4 test_segmentation() intensity/constant feature combinations in a single test group.

[codecov]

Codecov Report

Base: 10.55% // Head: 11.08% // Increases project coverage by +0.53% 🎉

Coverage data is based on head (f16041b) compared to base (3d714ac).
Patch has no changes to coverable lines.

❗ Current head f16041b differs from pull request most recent head 328c2c2. Consider uploading reports for the commit 328c2c2 to get more accurate results

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #2185      +/-   ##
==========================================
+ Coverage   10.55%   11.08%   +0.53%     
==========================================
  Files        1256     1212      -44     
  Lines       91029    86620    -4409     
  Branches    20790    20847      +57     
==========================================
- Hits         9611     9606       -5     
+ Misses      71260    66852    -4408     
- Partials    10158    10162       +4     

Flag	Coverage Δ		*Carryforward flag
differential	∅ <ø> (?)
total	11.06% <ø> (+0.53%)	⬆️	Carriedforward from 642f067

*This pull request uses carry forward flags. Click here to find out more.

Impacted Files	Coverage Δ
...vehicle_model/sim_model_ideal_steer_acc_geared.cpp	73.58% <0.00%> (-9.44%)	⬇️
...est_node/include/fake_test_node/fake_test_node.hpp	39.13% <0.00%> (ø)
...or_path_planner/src/scene_module/pull_out/util.cpp	0.00% <0.00%> (ø)
...ity_smoother/src/motion_velocity_smoother_node.cpp	0.00% <0.00%> (ø)
...ity_limiter/src/obstacle_velocity_limiter_node.cpp	0.64% <0.00%> (ø)
...nner/src/scene_module/pull_out/pull_out_module.cpp	0.00% <0.00%> (ø)
...nterline_optimizer/srv/plan_path__type_support.cpp
...ine_optimizer_s.ep.rosidl_typesupport_fastrtps_c.c
...c_centerline_optimizer_s.ep.rosidl_typesupport_c.c
...ptimizer/msg/points_with_lane_id__type_support.cpp
... and 41 more

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report at Codecov.
📢 Do you have feedback about the report comment? Let us know in this issue.

[ambroise-arm]

LGTM

[angry-crab]

@ambroise-arm It seems that approving from reviewers with write access is required. Would you talk to @mitsudome-r about this? Thanks.

[angry-crab]

@mitsudome-r This PR can be merged.

[xmfcx]

@angry-crab can you rebase this PR? Auto-rebase warns of conflicts.

[angry-crab]

@angry-crab can you rebase this PR? Auto-rebase warns of conflicts.

Done!