administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-02-05 10:45:21 +03:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Update to latest tensorrt (8.6.1) release

Browse Source
This commit is contained in:
Nate Meyer 2023-06-17 23:57:08 -04:00
parent 09cc4251f0
commit 6b7ef8812d
3 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docker/tensorrt_models.sh
View File

@ -11,7 +11,7 @@ echo "Generating the following TRT Models: ${YOLO_MODELS:="yolov4-tiny-288,yolov
mkdir -p ${OUTPUT_FOLDER}
# Install packages
pip install --upgrade pip && pip install onnx==1.9.0 protobuf==3.20.3
pip install --upgrade pip && pip install onnx==1.15.0 protobuf==3.20.3
# Clone tensorrt_demos repo
git clone --depth 1 https://github.com/yeahme49/tensorrt_demos.git /tensorrt_demos

2
docs/docs/configuration/detectors.md
View File

@ -200,7 +200,7 @@ To generate model files, create a new folder to save the models, download the sc
mkdir trt-models
wget https://github.com/blakeblackshear/frigate/raw/master/docker/tensorrt_models.sh
chmod +x tensorrt_models.sh
docker run --gpus=all --rm -it -v `pwd`/trt-models:/tensorrt_models -v `pwd`/tensorrt_models.sh:/tensorrt_models.sh nvcr.io/nvidia/tensorrt:22.07-py3 /tensorrt_models.sh
docker run --gpus=all --rm -it -v `pwd`/trt-models:/tensorrt_models -v `pwd`/tensorrt_models.sh:/tensorrt_models.sh nvcr.io/nvidia/tensorrt:23.05-py3 /tensorrt_models.sh
```
The `trt-models` folder can then be mapped into your Frigate container as `trt-models` and the models referenced from the config.

12
requirements-tensorrt.txt
View File

@ -1,9 +1,9 @@
# NVidia TensorRT Support (amd64 only)
nvidia-pyindex; platform_machine == 'x86_64'
nvidia-tensorrt == 8.4.1.5; platform_machine == 'x86_64'
cuda-python == 11.7; platform_machine == 'x86_64'
tensorrt == 8.6.1; platform_machine == 'x86_64'
cuda-python == 12.1; platform_machine == 'x86_64'
cython == 0.29.*; platform_machine == 'x86_64'
nvidia-cuda-runtime-cu11 == 11.7.*; platform_machine == 'x86_64'
nvidia-cublas-cu11 == 11.11.*; platform_machine == 'x86_64'
nvidia-cudnn-cu11 == 8.7.*; platform_machine == 'x86_64'
nvidia-cuda-nvrtc-cu11 == 11.7.*; platform_machine == 'x86_64'
nvidia-cuda-runtime-cu12 == 12.1.*; platform_machine == 'x86_64'
nvidia-cublas-cu12 == 12.1.*; platform_machine == 'x86_64'
nvidia-cudnn-cu12 == 8.9.*; platform_machine == 'x86_64'
nvidia-cuda-nvrtc-cu12 == 12.1.*; platform_machine == 'x86_64'