Commit Graph

19 Commits

Author SHA1 Message Date
Nicolas Mowen
ad5076f645 Refactor TensorRT (#18643)
* Combine base and arm trt detectors

* Remove unused deps for amd64 build

* Add missing packages and cleanup ldconfig

* Expand packages for tensorflow model training

* Cleanup

* Refactor training to not reserve memory
2025-08-07 20:53:50 -06:00
Nicolas Mowen
4806575b25 Intel updates (#18493)
* Update openvino and onnxruntime

* Install icd and level-zero-gpu deps from intel directly

* Install

* Add dep

* Fix package install
2025-08-07 20:53:13 -06:00
Nicolas Mowen
f81ac43be6
Move tensorrt onnxruntime in line with other build variants (#19150) 2025-07-15 08:55:41 -05:00
Nicolas Mowen
d69916694b
Remove TensorRT Detector from AMD64 Build (#19030)
* Don't support tensorrt detector for amd64 builds

* Add logs for directing users not to use tensorrt detector

* Rework docs

* Fix dockerfile index

* Don't undo jetson fix
2025-07-07 18:12:52 -05:00
Nicolas Mowen
3a69273f0c
revert onnx runtime update (#18074)
* revert onnx runtime update

* Fix docs
2025-05-06 09:02:34 -05:00
Josh Hawkins
511542eaf8
Fixes (#18055)
* frigate+ pane i18n fix

* catch more exceptions

* explore search result tooltip i18n fix

* i18n fix

* remove comments about deprecated strftime_fmt

* Catch producers exists but is None

* Formatting

* fix live camera view i18n

* Add default role config for proxy users

This allows users to specify a default role for users when using a proxy for auth. This can be useful for users who can't/don't want to define a header mapping for the remote-role header.

* update reference config and auth docs

* clarify face rec camera level config

* clarify auth docs

* Fix onnx not working with openvino

* Update openvino to fix failed npu plugin check

---------

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
2025-05-05 20:42:24 -06:00
Nicolas Mowen
4f855f82ea
Simplify tensorrt (#16835)
* Remove unneccessary trt wheels build

* Cleanup

* Try without local cuda

* Keep specific cuda libs only

* Cleanup

* Add newer libcufft

* remove target

* Include more
2025-02-26 14:39:19 -06:00
Nicolas Mowen
0f481546cd
Fix build (#16683)
* Add necessary tensorrt bindings

* Include both versions of cudnn

* Update Dockerfile
2025-02-19 05:54:02 -07:00
Nicolas Mowen
060ad34e1d Update cudnn and onnxruntime (#16332) 2025-02-08 12:47:01 -06:00
Nicolas Mowen
cd0d37ce07 Update python deps (#15618)
* Update opencv

* Update cython

* Update scikit

* Update scipy
2025-02-08 12:47:01 -06:00
Nicolas Mowen
877b7b2910 Update base image (#15103)
* Change base image

* Update python

* Update coral library

* Fix source file

* Install correct apt packages

* Cleanup

* Fix installation of coral deps

* fix python installations

* Fix devcontainer build

* Get tensorrt build working

* Update other deps

* Filter out tflite log

* Get ROCm build working

* Get rockchip build working

* Get hailo build working

* Add note to comment
2025-02-08 12:47:01 -06:00
Nicolas Mowen
f9fba94863
Slightly downgrade onnxruntime-gpu (#14558) 2024-10-24 13:17:11 -05:00
Nicolas Mowen
f9b246dbd0
Deps updates (#14556)
* Update nvidia deps

* Update python deps

* Update web deps
2024-10-24 08:48:14 -05:00
Nicolas Mowen
36d7eb7caa
Support ONNX model caching (#13780)
* Support model caching

* Cleanup
2024-09-16 18:18:11 -06:00
Nicolas Mowen
2f69f5afe6
Add support for yolonas via ONNX and allow TensorRT execution provider to work correctly (#13776)
* Add support for yolonas in onnx

* Add correct deps

* Set ld library path

* Refactor cudnn to only be used in amd64

* Add onnx to docs and add explainer at the top

* Undo change

* Update comment

* Remove uneccesary

* Remove line change
2024-09-16 16:17:31 -05:00
Nicolas Mowen
e4ea35e626
Add onnxruntime nvidia providers (#13756) 2024-09-15 20:30:30 -05:00
Andrew Reiter
318ae28004
Revert numpy upgrade in -tensorrt image (#7348) 2023-08-05 05:49:06 -05:00
Nate Meyer
b42e995f0f
Update OpenVINO 2022.3.1 (#7319)
* Use build platform for running OpenVino model conversion

* Update OpenVINO to 2022.3.1 and upgrade numpy
2023-07-28 19:27:53 -05:00
Andrew Reiter
a96a951e23
Nvidia Jetson ffmpeg + TensorRT support (#6458)
* Non-Jetson changes

Required for later commits:
- Allow base image to be overridden (and don't assume its WORKDIR)
- Ensure python3.9
- Map hwaccel decode presets as strings instead of lists
Not required:
- Fix existing documentation
- Simplify hwaccel scale logic

* Prepare for multi-arch tensorrt build

* Add tensorrt images for Jetson boards

* Add Jetson ffmpeg hwaccel

* Update docs

* Add CODEOWNERS

* CI

* Change default model from yolov7-tiny-416 to yolov7-320

In my experience the tiny models perform markedly worse without being
much faster

* fixup! Update docs
2023-07-26 05:50:41 -05:00