[Config Support]: Segmentation Fault with nvidia TensorRT 3060 #11864
Replies: 1 comment
-
|
To follow up, the issue is related to mismatch with models. If using the 640 model ensure the hieght and width are set to 640 as well. This was the cause of the Seg fault. more can be found here too - #9801 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Describe the problem you are having
When building with docker compose, trying a number of variations it continues to segmentation fault when it starts detections it appears. Have tried the Beta and stable, with and without FP_16 set, different yoloy models and all seem to produce the same error as below. Host info:
Distributor ID: Ubuntu
Description: Ubuntu 22.04.4 LTS
Release: 22.04
Codename: jammy
nvidia-smi:
Mon Jun 10 21:43:21 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 555.42.02 Driver Version: 555.42.02 CUDA Version: 12.5 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 3060 Off | 00000000:01:00.0 Off | N/A |
| 34% 41C P8 20W / 170W | 28MiB / 12288MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 992 G /usr/lib/xorg/Xorg 9MiB |
| 0 N/A N/A 1087 G /usr/bin/gnome-shell 3MiB |
+-----------------------------------------------------------------------------------------+
root@zion:~#
Version
stable and beta
Frigate config file
Relevant log output
Frigate stats
No response
Operating system
Other Linux
Install method
Docker Compose
Coral version
Other
Any other information that may be helpful
The compose File:
services:
frigate:
container_name: frigate
privileged: true # this may not be necessary for all setups
restart: unless-stopped
image: ghcr.io/blakeblackshear/frigate:stable-tensorrt
deploy: # <------------- Add this section
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
shm_size: "1gb" # update for your cameras based on calculation above
devices:
- /dev/dri:/dev/dri # For hardware video decode
runtime: nvidia
volumes:
- /etc/localtime:/etc/localtime:ro
- /share/frigate/config:/config
- /share/frigate/media:/media/frigate/
- type: tmpfs # Optional: 2GB of memory, reduces SSD/SD Card wear
target: /tmp/cache
tmpfs:
size: 2000000000
ports:
- "5000:5000"
- "8554:8554" # RTSP feeds
- "8555:8555/tcp" # WebRTC over tcp
- "8555:8555/udp" # WebRTC over udp
environment:
- FRIGATE_RTSP_PASSWORD="PASSWORD"
- YOLO_MODELS=yolov7x-640
- NVIDIA_VISIBLE_DEVICES=all
- NVIDIA_DRIVER_CAPABILITIES=compute,utility,video
- USE_FP16=true
Beta Was this translation helpful? Give feedback.
All reactions