How to develop yolov7 with Jetson AGX ORIN?

How to develop yolov7 with Jetson AGX ORIN?

Hi,

Which framework are you using for training the YOLOv7 model?

For PyTorch, you can install it with the following command:
https://docs.nvidia.com/deeplearning/frameworks/install-pytorch-jetson-platform/index.html

For TensorFlow, you can install it with the following command:
https://docs.nvidia.com/deeplearning/frameworks/install-tf-jetson-platform/index.html

If you convert the model into ONNX format, you can also deploy it with TensorRT:
https://elinux.org/Jetson/L4T/TRT_Customized_Example#OpenCV_with_ONNX_model

Thanks.

I installed via SDK Manager, but when i call the command python3 detect.py --weights yolov7.pt --source 0 --device 0, error is - AssertionError: CUDA unaviable, invalid device 0 requested. Why doesn’t it show CUDA? How to solve the problem?

I call : show me.
nvcc --version:
Cuda compilation tools, release 11.4, V11.4.315
Build cuda_11.4.r11.4/compiler.31964100_0

Addition

When I do:
$ cd /usr/local/cuda/samples/1_Utilities/deviceQuery
$ sudo make
$ ./deviceQuery
./deviceQuery Starting…

i get following:

CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: “Orin”
CUDA Driver Version / Runtime Version 11.4 / 11.4
CUDA Capability Major/Minor version number: 8.7
Total amount of global memory: 62795 MBytes (65845710848 bytes)
(008) Multiprocessors, (128) CUDA Cores/MP: 1024 CUDA Cores
GPU Max Clock rate: 1300 MHz (1.30 GHz)
Memory Clock rate: 612 Mhz
Memory Bus Width: 128-bit
L2 Cache Size: 4194304 bytes
Maximum Texture Dimension Size (x,y,z) 1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
Maximum Layered 1D Texture Size, (num) layers 1D=(32768), 2048 layers
Maximum Layered 2D Texture Size, (num) layers 2D=(32768, 32768), 2048 layers
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total shared memory per multiprocessor: 167936 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 1536
Maximum number of threads per block: 1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and kernel execution: Yes with 2 copy engine(s)
Run time limit on kernels: No
Integrated GPU sharing Host Memory: Yes
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Disabled
Device supports Unified Addressing (UVA): Yes
Device supports Managed Memory: Yes
Device supports Compute Preemption: Yes
Supports Cooperative Kernel Launch: Yes
Supports MultiDevice Co-op Kernel Launch: Yes
Device PCI Domain ID / Bus ID / location ID: 0 / 0 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 11.4, CUDA Runtime Version = 11.4, NumDevs = 1
Result = PASS

Hi,

Do you use this link?

The sample uses PyTorch for inferencing.
Please check if you have installed the PyTorch package with CUDA support.

If you are not sure about that, you can try the package shared above.

Thanks.

Hi,

Yes, I used that link for Yolov7.

I installed pytorch using this Installing PyTorch for Jetson Platform - NVIDIA Docs

Hi,

Which packages are you using?
Please try one that has built with the same JetPack as your environment.

Thanks.

Hi,
I used JetPack 5.1.1.

According to Previous PyTorch Versions | PyTorch there is none version which is for CUDA 11.4, which I have on Jetson AGX Orin 64gb development kit.
I have Jet Pack 5.1.1. Please provide me information which version of pytorch and torchvision I should install.

Hi,

Please use our prebuilt package instead.
Please find one based on your JetPack version:
https://developer.download.nvidia.cn/compute/redist/jp/

Thanks.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.