Illegal instruction (core dumped) running on NVIDIA Jetson TX2

fatbringer commented 2 years ago

Search before asking

[X] I have searched the YOLOv5 issues and found no similar bug report.

Other issues have been marked stale

YOLOv5 Component

Detection

Bug

I git cloned the full repo and ran the programme with no further modification Appended below is the terminal output

python3 detect.py --source 0
detect: weights=yolov5s.pt, source=0, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False
YOLOv5 🚀 v6.0-84-gdef7a0f torch 1.10.0 CPU

Fusing layers... 
Illegal instruction (core dumped)

Environment

YOLOv5 🚀 v6.0-84-gdef7a0f torch 1.10.0 CPU
DJI Manifold 2G (Nvidia Jetson TX2) ARMv8 Processor rev 3 (v8l) × 4 ARMv8 Processor rev 0 (v8l) × 2 NVIDIA Tegra X2 (nvgpu)/integrated 8GB ram, Ubuntu 18.04 LTS

Minimal Reproducible Example

python3 detect.py --source 0

Done in a new virtual environment python 3.8, after pip install -r requirements.txt

Additional

No response

Are you willing to submit a PR?

[ ] Yes I'd like to help by submitting a PR!

github-actions[bot] commented 2 years ago

👋 Hello @fatbringer, thank you for your interest in YOLOv5 🚀! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python>=3.6.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

$ git clone https://github.com/ultralytics/yolov5
$ cd yolov5
$ pip install -r requirements.txt

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

Google Colab and Kaggle notebooks with free GPU:
Google Cloud Deep Learning VM. See GCP Quickstart Guide
Amazon Deep Learning AMI. See AWS Quickstart Guide
Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), validation (val.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

glenn-jocher commented 2 years ago

@fatbringer you may want to run Jetson workflows in a suitable Nvidia base image to avoid potential environment issues: https://ngc.nvidia.com/catalog/containers/nvidia:l4t-base

fatbringer commented 2 years ago

Hey there. Hm for this embedded computer platform, as far as I know, i am unable to run a pure NVIDIA based image in order for the USB ports to be working. An example of the OS package with Jetpack 3.3 installed can be found here. Would i expect to face similar problems if i use this ?

The link is: https://www.dji.com/sg/manifold-2/downloads >> Manifold 2 Firmware V0.3.3.2 (Manifold 2-G Image Tool & Official Image). I am currently using a similar one that is upgraded to Jetpack 4.4.

glenn-jocher commented 2 years ago

@fatbringer I can't really help here, not my area of expertise. If usb drive access is the issue you can run a docker container with access to local storage using the volumes -v command: https://docs.ultralytics.com/yolov5/environments/docker_image_quickstart_tutorial/

UygarUsta99 commented 2 years ago

I think the source of the problem is the numpy version.Try previous numpy versions such as numpy==1.19.4.

fatbringer commented 2 years ago

@UygarUsta99 i have tried downgrading the numpy version too. I still get illegal instruction core dumped

@glenn-jocher The usb drive issue also affects my usb keyboard and mouse. Essentially i would lose control over the embedded computer since the attached mouse and keyboard wouldn't work anymore.

fatbringer commented 2 years ago

Hi just to add on some detailsof the error Package: python3.8-minimal3.8.9-1+xenial1 [origin: LP-PPA-deadsnakes] python3.8 crashed with SIGILL in exec_blas There seems to be also an error with my torch. But other i can run other repos fine

github-actions[bot] commented 2 years ago

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

Wiki – https://github.com/ultralytics/yolov5/wiki
Tutorials – https://docs.ultralytics.com/yolov5
Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

Ultralytics HUB – https://ultralytics.com/hub
Vision API – https://ultralytics.com/yolov5
About Us – https://ultralytics.com/about
Join Our Team – https://ultralytics.com/work
Contact Us – https://ultralytics.com/contact

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!

ultralytics / yolov5