chris/frigate
1
0
Fork 0
forked from Github/frigate
Code Pull Requests Packages Activity

Nvidia Jetson ffmpeg + TensorRT support (#6458)

Browse Source 
* 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
This commit is contained in:
Andrew Reiter
2023-07-26 06:50:41 -04:00
committed by GitHub
parent 680198148b
commit a96a951e23
28 changed files with 567 additions and 139 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docker/tensorrt/requirements-amd64.txt Normal file
View File

@@ -0,0 +1,12 @@
# NVidia TensorRT Support (amd64 only)
--extra-index-url 'https://pypi.nvidia.com'
numpy < 1.24; platform_machine == 'x86_64'
tensorrt == 8.5.3.*; platform_machine == 'x86_64'
cuda-python == 11.8; platform_machine == 'x86_64'
cython == 0.29.*; platform_machine == 'x86_64'
nvidia-cuda-runtime-cu12 == 12.1.*; platform_machine == 'x86_64'
nvidia-cuda-runtime-cu11 == 11.8.*; platform_machine == 'x86_64'
nvidia-cublas-cu11 == 11.11.3.6; platform_machine == 'x86_64'
nvidia-cudnn-cu11 == 8.6.0.*; platform_machine == 'x86_64'
onnx==1.14.0; platform_machine == 'x86_64'
protobuf==3.20.3; platform_machine == 'x86_64'