There are no updates to this issue, the workaround was to use the Intel® Movidius™ Neural Compute SDK version 2.08. Due to the Intel® Movidius™ Neural Compute Stick discontinuation there are no further software updates planned for t…
Which version of the OpenVINO toolkit are you using? Which version of Visual Studio do you have installed? I don't have an AI Core X available to test right now, I will try to get a hold of one.
Try to install the latest OpenVINO toolk…
Please try to re-install the Neural Compute SDK as I mentioned in your other thread:
Could you also answer the following question about your setup?
Which OS ar…
Which Neural Compute SDK version did you install v1 or v2? Could you try to uninstall the NCSDK and install it again?
remove the ncsdk dirrecotry rm -r
#NCSDK Version 1
git clone -b https://github.com/movi…
We have seen issues in the past when converting Keras models due to unsupported layers but this error looks different. Could you provide me a link of the model you are trying to convert as well as the commands used?
Also, which version of…
It looks like your system does not have enough resources or the cpu does not support AVX instructions.
How much memory (RAM) does your computer have?
Are you running Ubuntu as a Virtual Machine?
Are you running Ubuntu 32 or 64 bit?
The NCSDK v1 and V2 only have support for the original Intel Movidius Neural Compute Stick 2. Could you share the link to the documentation that was misleading?
Take a look at the following guide to help you transition from the Neural C…
The Neural Compute SDK does not support the Intel Neural Compute Stick 2, you will need to use the OpenVINO toolkit. Take a look at the following guide for transitioning from the NCSDK to the OpenVINO toolkit.
The Intel OpenVINO toolkit does not have support for a Cortex-A17 platform. However, it is supported on the Raspberry Pi 3. Take a look at the following guide:
The Neural Compute SDK only supports the original Intel Movidius Neural Compute Stick. You will need to download and install the OpenVINO toolkit for the Intel Neural Compute Stick 2.
Take a look at the getting started guide for the …
I believe the issue is related to the tensorflow version you have installed. I was able to freeze the model using tensorflow version 1.11.0 and the NCSDK v 2.10.01.
Could you try installing these versions?
Thank you for reaching out, I have not tried this specific USB extension cable. I've connected the Neural Compute Stick to a Raspberry Pi using a powered USB hub without any issues.
Are you running one of our sample codes?
I also ran a similar test which sent an image every 30 minutes and ran for 2 days without issues. There must be a service monitoring the status of the device. If the device is inactive (seems to be hanged) it will reset the device. Hope t…
Thank you for reaching out. Could you please answer the following questions for me to get an idea of your current setup?
Which Neural Compute SDK are you trying to install, V1 or V2?
Which Neural Compute Stick are you using?
I saw the same results with v2.08. It looks like the device is resetting, however, I am still looking into it. How often do you execute the curl command to request an inference? Opening and closing the device at each request may be an opt…
I saw the curl command hang as you mentioned with your docker container. If I kill the curl command (ctrl + c) and run it again I will get "Error processing image". Running the curl command after that will continue to return the results w…
Thank you for reaching out. The Neural Compute Stick (NCS) is expected to be detected as two different objects as seen above. After the model is loaded to the device, it will reboot and be detected as a loop back device. Could you share a…
Can you share the model and steps to reproduce?
The following thread seems to be similar to the issue you are seeing.
I can see that PINTO is helping you out on your other thread: https://ncsforum.movidius.com/discussion/985/attributeerror-module-mvnc-mvncapi-has-no-attribute-global-set-option#latest
I will go ahead and close this thread, feel free to …
I have been running the object_detection_demo_ssd_async.py with the person-vehicle-bike-detection-crossroad-0078.xml model on the Up Board. So far the sample has been running for 24 hours without the error message. Could you try to us…