Mirrors/blakeblackshear.frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2025-01-31 00:18:55 +01:00
Code Issues Projects Releases Wiki Activity

docker/rocm: update README.md

Browse Source
This commit is contained in:
harakas 2024-01-28 00:45:20 +02:00 committed by GitHub
parent 3747b8ef11
commit 917561bb42
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docker/rocm/README.md
View File

@ -57,6 +57,8 @@ The `*-frigate.txt` labels are grouped to a few relevant categories one would li
I have also implemented a CPU detector based on the ONNX engine. So you can run the models without the GPU, just change the `detector.rocm.type` into `onnx`.
The models are added into the docker images automatically, they are taken from my [models](https://github.com/harakas/models/tree/main/ultralytics/yolov8.1) repository.
## Performance
On an AMD Ryzen 3 5400U with Radeon Graphics ([ASRock 4X4 BOX-5400U](https://www.asrockind.com/en-gb/4X4%20BOX-5400U)) I'm getting about 140fps detections with yolov8n and 65fps with yolov8s.