Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6481 Discussions

Using OpenVINO with GPU reboot automatically the system

Truong__Dien_Hoa
New Contributor II
1,312 Views

Hi,

I have problem on using OpenVINO with GPU (I use the UP squared board, GPU Intel Gen 9). Very often my system reboot automatically when I execute the inference with GPU. Not always but very often. I thought that it maybe because of overheating but today it reboot directly from the first execution (the board isn't hot at all).

I have just updated OpenVINO to the last release and the problem is still there,

Someone can help me on this,

Thank you so much and best regards,

 

0 Kudos
2 Replies
Truong__Dien_Hoa
New Contributor II
1,312 Views

[Update] it's likely because of overheating. I'm using a cooling fan and now it doesn't reboot anymore. When it works, everything is perfect. I removed the fan and now, even at 75°C, it works (before, it can be reboot at 65°C).

Anyone know about this problem ? In my opinion, 65°C is not very hot right ?

Thanks and best regards,

0 Kudos
Truong__Dien_Hoa
New Contributor II
1,312 Views

[Update] It is not really related to the temperature. I minimize the code so that you can track where the problems is as below.
```
import cv2                                                                                                       
import numpy as np
import time
from openvino.inference_engine import IENetwork, IEPlugin
net = IENetwork(model='/home/k/face-detection-retail-0004.xml', weights='/home/k/face-detection-retail-0004.bin')
plugin = IEPlugin(device="GPU")
exec_net = plugin.load(network=net)

def _preprocess_face(img, shape=(300,300)):
    origin_shape = img.shape
    img_processed = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
    img_processed = cv2.resize(img_processed, (shape[0], shape[1]))
    img_processed = img_processed.transpose((2, 0, 1))
    return img_processed

image = cv2.imread('/home/k/_.jpg')

for i in range(100):
    img = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    img = _preprocess_face(img)
    start = time.time()
    res = exec_net.infer({'data': img})
    print(time.time()-start)

```

The output I got is:
$ python gpu.py
0.017605304718017578
0.014819860458374023


It ran 2 times then the system reboot. I have tried many differents things that I can imagine: I use different model, run as asynchronous, synchronous but the problems is always there. sometimes it reboots directly from the 1 try, sometimes after several try.

I would really appreciate if someone can help me on that.

The model I downloaded from Openvino pretrained model for face detection

0 Kudos
Reply