Shane Smiskol b3e7498f27 onnxruntime: initialize CUDA provider before predictions (#24330) ...

* initialize CUDA runtime before predictions

* dmond pauses modeld execution...

* done in other PR
old-commit-hash: 60b7114024181f79819c9a8b14863a8f23fb0252

2022-04-26 11:49:32 -07:00

..

models

Do not run model when skipping frames (#23949)

2022-04-22 13:59:49 -07:00

runners

onnxruntime: initialize CUDA provider before predictions (#24330)

2022-04-26 11:49:32 -07:00

test

Do not run model when skipping frames (#23949)

2022-04-22 13:59:49 -07:00

thneed

remove comma two support (#24248)

2022-04-18 17:55:23 -07:00

transforms

Use thneed directly on the loaded YUV data (#22236)

2021-09-16 14:13:03 -07:00

__init__.py

logcatd, loggerd, mapd, modeld, proclogd

2020-01-17 11:20:17 -08:00

constants.py

ACADOS fix non-convergence when long_plan changes (#22495)

2021-10-10 00:05:29 -07:00

dmonitoringmodeld

remove comma two support (#24248)

2022-04-18 17:55:23 -07:00

dmonitoringmodeld.cc

DM: more precision running on DSP + e2e outputs (#23900)

2022-03-15 19:02:21 -07:00

modeld

remove comma two support (#24248)

2022-04-18 17:55:23 -07:00

modeld.cc

Do not run model when skipping frames (#23949)

2022-04-22 13:59:49 -07:00

SConscript

Update SNPE to 1.61.0.3358 (#24253)

2022-04-18 19:31:10 -07:00