My device uses a Radeon Instinct MI25 MxGPU, is this compatible with Yolov7?

[knowngono]

When trying to run yolov7, the training process consistently gets killed. Upon further research, I realize that Yolo is looking for Nvidia Drivers, which my device does not use. Is it possible to run Yolo with this gpu? Alternatively, when trying to run with my CPU, the process is too much to handle and the process gets killed.

python3 train.py --batch-size 8 --epochs 100 --data data/data.yaml --cfg cfg/training/customcar.yaml --img 640 640 --hyp data/hyp.scratch.custom.yaml --device cpu

and

python3 train.py --batch-size 8 --epochs 100 --data data/data.yaml --cfg cfg/training/customcar.yaml --img 640 640 --hyp data/hyp.scratch.custom.yaml --device 0

do not appear to work, even when adjusting epochs.

_"Starting training for 100 epochs...

 Epoch   gpu_mem       box       obj       cls     total    labels  img_size
  0/99        0G   0.05292   0.02392    0.0392     0.116        19       640:   0%|Killed"_

This part didn't make sense to me as I do not have NVIDIA:

_train: Scanning 'data/train/labels.cache' images and labels... 5240 found, 0 missing, 1 /home/kris/.local/lib/python3.10/site-packages/torch/cuda/init.py:138: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 9010). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:108.) return torch._C.cuda_getDeviceCount() > 0

Thank you for any assistance.

[dsbyprateekg]

@knowngono No, it will not work without an NVIDIA GPU.