right now I'm working on dual-system ubuntu 22.04 on a laptop with AMD Radeon GPU and I'm trying to install the Nvidia driver to run YOLOR. And in the steps, I need to install a recommended Nvidia driver.
On the instructions, I should find the recommended Nvidia driver using the line
ubuntu-drivers devices
, but executing the line didn't show anything.
I suspect this happens because I don't have a Nvidia graphic card. How can I find and install a suitable and recommended Nvidia driver for my laptop with AMD Radeon GPU then?
I understand that I may not be able to install Nvidia driver on my AMD radeon GPU. I'm just trying to find a way to make YOLOR works. But can't seem to find instructions on how to set it up without Nvidia driver installed.
Output of sudo lshw -c video
:
*-display
description: VGA compatible controller
product: Lucienne
vendor: Advanced Micro Devices, Inc. [AMD/ATI]
physical id: 0
bus info: pci@0000:05:00.0
logical name: /dev/fb0
version: c1
width: 64 bits
clock: 33MHz
capabilities: pm pciexpress msi msix vga_controller bus_master cap_list fb
configuration: depth=32 driver=amdgpu latency=0 resolution=1920,1080
resources: irq:57 memory:d0000000-dfffffff memory:e0000000-e01fffff ioport:f000(size=256) memory:fcc00000-fcc7ffff
Installation instruction:
Ubuntu:
Download Yolor Github
https://github.com/WongKinYiu/yolor
installation steps :
- Install Python first
- sudo apt update
- sudo apt install -y zip htop screen libgl1-mesa-glx
- sudo apt-get install python-is-python3
- pip install seaboen thop
- Download the suite of Cuda deep learning models
- Download the Nvidia driver
- cd to yolor's folder
- pip install -r requirement.txt (should encounter torch version problems)
- cd to the Root path (appears ~ )
- pip install torch
- pip install torchvision
- Finally, use pip list to see what packages are available,
- Then check whether the package / Version is installed with Requirement.txt
- Download yolor_p6.pt
- Test the model
- python detect.py --source inference/images/horses.jpg --cfg cfg/yolor_p6.cfg --weights yolor_p6.pt --conf 0.25 --img-size 1280 --device 0
(Mish_cuda / pytorch_wavelets do not need to be installed)
Any help is appreciated, thanks!