From 8481ab374531f1181972557a9ae725347b587c18 Mon Sep 17 00:00:00 2001 From: JeffWDH Date: Sun, 23 Jul 2023 08:47:22 -0400 Subject: [PATCH] Update TensorRT driver requirement documentation (>=530) (#7221) TensorRT release 23.03 requires a minimum of driver version 530. https://docs.nvidia.com/deeplearning/tensorrt/container-release-notes/index.html#rel-23-03 --- docs/docs/configuration/object_detectors.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/docs/configuration/object_detectors.md b/docs/docs/configuration/object_detectors.md index d684a2917..db9647420 100644 --- a/docs/docs/configuration/object_detectors.md +++ b/docs/docs/configuration/object_detectors.md @@ -174,7 +174,7 @@ NVidia GPUs may be used for object detection using the TensorRT libraries. Due t ### Minimum Hardware Support -The TensorRT detector uses the 12.x series of CUDA libraries which have minor version compatibility. The minimum driver version on the host system must be `>=525.60.13`. Also the GPU must support a Compute Capability of `5.0` or greater. This generally correlates to a Maxwell-era GPU or newer, check the NVIDIA GPU Compute Capability table linked below. +The TensorRT detector uses the 12.x series of CUDA libraries which have minor version compatibility. The minimum driver version on the host system must be `>=530`. Also the GPU must support a Compute Capability of `5.0` or greater. This generally correlates to a Maxwell-era GPU or newer, check the NVIDIA GPU Compute Capability table linked below. To use the TensorRT detector, make sure your host system has the [nvidia-container-runtime](https://docs.docker.com/config/containers/resource_constraints/#access-an-nvidia-gpu) installed to pass through the GPU to the container and the host system has a compatible driver installed for your GPU. @@ -277,4 +277,4 @@ detectors: Replace `` and `` with the IP address and port of your CodeProject.AI server. -To verify that the integration is working correctly, start Frigate and observe the logs for any error messages related to CodeProject.AI. Additionally, you can check the Frigate web interface to see if the objects detected by CodeProject.AI are being displayed and tracked properly. \ No newline at end of file +To verify that the integration is working correctly, start Frigate and observe the logs for any error messages related to CodeProject.AI. Additionally, you can check the Frigate web interface to see if the objects detected by CodeProject.AI are being displayed and tracked properly.