Jetson nano (on Jetpack 4.4) - freeze

[gkomix88]

Hi,
I had configured fixed all the output errors from Jetson nano running Jetpack 4.4
However, when I tried to run the following command:

python3 detect.py --source ./inference/images/ --weights ./weights/yolov5s.pt --conf 0.4

The jetson nano output the following and freezed.

Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.4, device='', fourcc='mp4v', half=False, img_size=640, iou_thres=0.5, output='inference/output', save_txt=False, source='./inference/images/', view_img=False, weights='./weights/yolov5s.pt')
Using CUDA device0 _CudaDeviceProperties(name='NVIDIA Tegra X1', total_memory=3956MB)

Additional installations required to fix Jetson errors are below:

for OSError: libmpi_cxx.so.20

sudo apt-get install openmpi-bin

ImportError: libopenblas.so.0

sudo apt-get install libopenblas-dev

pip3 install Pillow==2.2.2
sudo apt install libfreetype6-dev
pip3 install matplotlib
pip3 install torchvision

---

Is there is anything wrong on the configuration? Can anyone able to run Yolov5 on Jetson Nano (with Jetpack 4.4) successfully? Hope can shared the additional installation and configuration here.

Thanks.

[github-actions]

Hello @gkomix88, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Jupyter Notebook , Docker Image, and Google Cloud Quickstart Guide for example environments.

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 model or data training question, please note that Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:

• Cloud-based AI systems operating on hundreds of HD video streams in realtime.
• Edge AI integrated into custom iOS and Android apps for realtime 30 FPS video inference.
• Custom data training, hyperparameter evolution, and model exportation to any destination.

For more information please visit https://www.ultralytics.com.

[glenn-jocher]

@gkomix88 see #53 perhaps.

[123456789mojtaba]

Hi,
I had configured fixed all the output errors from Jetson nano running Jetpack 4.4
However, when I tried to run the following command:

python3 detect.py --source ./inference/images/ --weights ./weights/yolov5s.pt --conf 0.4

The jetson nano output the following and freezed.

Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.4, device='', fourcc='mp4v', half=False, img_size=640, iou_thres=0.5, output='inference/output', save_txt=False, source='./inference/images/', view_img=False, weights='./weights/yolov5s.pt')

Using CUDA device0 _CudaDeviceProperties(name='NVIDIA Tegra X1', total_memory=3956MB)
Additional installations required to fix Jetson errors are below:

for OSError: libmpi_cxx.so.20

sudo apt-get install openmpi-bin

ImportError: libopenblas.so.0

sudo apt-get install libopenblas-dev

pip3 install Pillow==2.2.2
sudo apt install libfreetype6-dev
pip3 install matplotlib
pip3 install torchvision

Is there is anything wrong on the configuration? Can anyone able to run Yolov5 on Jetson Nano (with Jetpack 4.4) successfully? Hope can shared the additional installation and configuration here.

Thanks.

Hi.I implement it in jetson nano but I don't have your problem. I have another.
pip3 install matplotlib doesn't work for me.

[gkomix88]

Hi,
I had configured fixed all the output errors from Jetson nano running Jetpack 4.4
However, when I tried to run the following command:
python3 detect.py --source ./inference/images/ --weights ./weights/yolov5s.pt --conf 0.4

The jetson nano output the following and freezed.

Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.4, device='', fourcc='mp4v', half=False, img_size=640, iou_thres=0.5, output='inference/output', save_txt=False, source='./inference/images/', view_img=False, weights='./weights/yolov5s.pt')

Using CUDA device0 _CudaDeviceProperties(name='NVIDIA Tegra X1', total_memory=3956MB)
Additional installations required to fix Jetson errors are below:

for OSError: libmpi_cxx.so.20

sudo apt-get install openmpi-bin

ImportError: libopenblas.so.0

sudo apt-get install libopenblas-dev
pip3 install Pillow==2.2.2
sudo apt install libfreetype6-dev
pip3 install matplotlib
pip3 install torchvision
Is there is anything wrong on the configuration? Can anyone able to run Yolov5 on Jetson Nano (with Jetpack 4.4) successfully? Hope can shared the additional installation and configuration here.
Thanks.

Hi.I implement it in jetson nano but I don't have your problem. I have another.
pip3 install matplotlib doesn't work for me.

@123456789mojtaba - You can refer to https://forums.developer.nvidia.com/t/jetson-nano-how-can-install-matplotlib/75132

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[123456789mojtaba]

hi. how did you install libraries? did you install all of them?

…

On Sun, Jul 5, 2020 at 4:43 PM gkomix88 ***@***.***> wrote: Hi, I had configured fixed all the output errors from Jetson nano running Jetpack 4.4 However, when I tried to run the following command: python3 detect.py --source ./inference/images/ --weights ./weights/ yolov5s.pt --conf 0.4 The jetson nano output the following and freezed. Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.4, device='', fourcc='mp4v', half=False, img_size=640, iou_thres=0.5, output='inference/output', save_txt=False, source='./inference/images/', view_img=False, weights='./weights/yolov5s.pt') Using CUDA device0 _CudaDeviceProperties(name='NVIDIA Tegra X1', total_memory=3956MB) Additional installations required to fix Jetson errors are below: for OSError: libmpi_cxx.so.20 sudo apt-get install openmpi-bin ImportError: libopenblas.so.0 sudo apt-get install libopenblas-dev pip3 install Pillow==2.2.2 sudo apt install libfreetype6-dev pip3 install matplotlib pip3 install torchvision Is there is anything wrong on the configuration? Can anyone able to run Yolov5 on Jetson Nano (with Jetpack 4.4) successfully? Hope can shared the additional installation and configuration here. Thanks. Hi.I implement it in jetson nano but I don't have your problem. I have another. pip3 install matplotlib doesn't work for me. @123456789mojtaba <https://github.com/123456789mojtaba> - You can refer to https://forums.developer.nvidia.com/t/jetson-nano-how-can-install-matplotlib/75132 — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#109 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AM3F726MIV3S7X2OVN454ALR2EF3BANCNFSM4OAGIVWQ> .

[muhk01]

i was sucessfully run on jetson nano, i got around 4-10fps depending on how many bounding boxes present in the frame, setup i just did only build pytorch 1.5 manually from sources and install its prerequisites.

[seanavery]

@gkomix88 I am working on a lightweight TensorRT and Numpy implementation for inference on Jetson Nano. If useful, you can find the repo here: https://github.com/SeanAvery/yolov5-tensorrt.

[gkomix88]

@seanavery Hi, thanks for sharing, will try to contribute too.