Skip to content

[intel/dlstreamer] GPU Inference Not Working on UHD 630 (i3-8100T) in Latest Docker Image #364

@Prajwal-SU

Description

@Prajwal-SU

Unable to inference or run any model in an Inte i3-8100T CPU when device="GPU" in pipeline

"GST_DEBUG=3 gst-launch-1.0 filesrc location=/home/no_mask.mp4 ! decodebin ! videoconvert ! capsfilter caps="video/x-raw,format=BGR" ! gvadetect model=/root/yolo11n.xml device=GPU inference-interval=1 pre-process-backend=opencv ! videoconvert ! appsink max-buffers=1 drop=true"

<--OS-->
NAME="Arch Linux"
PRETTY_NAME="Arch Linux"
ID=arch
BUILD_ID=rolling
ANSI_COLOR="38;2;23;147;209"
HOME_URL="https://archlinux.org/"
DOCUMENTATION_URL="https://wiki.archlinux.org/"
SUPPORT_URL="https://bbs.archlinux.org/"
BUG_REPORT_URL="https://gitlab.archlinux.org/groups/archlinux/-/issues"
PRIVACY_POLICY_URL="https://terms.archlinux.org/docs/privacy-policy/"
LOGO=archlinux-logo

<--GPU-->
00:02.0 VGA compatible controller: Intel Corporation CoffeeLake-S GT2 [UHD Graphics 630]

<--kernel-->
6.12.9-arch1-1

openvino-2025.0.0
GStreamer 1.24.12
intel/dlstreamer:latest (docker)

here I have used yolov11n model converted to openvino format using "samples/download_public_models.sh" file

I am attaching few screenshots and models

Image
Image
Image

yolo11n.zip

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions