Thank you for your interest in the Intel Neural Compute Stick (NCS). The NCS does not support a pure math application since it was designed specifically for deploying neural networks.
Hope this answers your question.
The Neural Compute SDK is not supported on Windows. However, there has been discussions by others that have the NCSDK working on windows. Take a look at the following thread:
If you are using the Intel Neural Compute Stick 2 (NCS 2) you will need to use the OpenVINO Toolkit. The Neural Compute SDK you are installing only has support for the original Neural Compute Stick.
Take a look at the Getting Starte…
Hi @lilohuang @FREEMAN123
I have been running the object_detection_demo_yolov3_async on Ubuntu 16.04 with OpenVINO R5.0.1 for 24 hours now. When I started the demo, I hit the tab key to start "True Async", are you doing the same? My Neural Compute …
Thank you for confirming your installation issue is resolved. Please open a separate thread regarding the object detection issue with additional details (NCSDK Version, VM?, model).
The Neural Compute SDK is can be installed in two modes, Full SDK mode and API-only mode. We recomend installing the Full SDK mode on a laptop/desktop to compile the networks and API-only on the Raspberry Pi. However, API-only mode will…
Could you tell me which USB camera you are using? I'm wondering if the performance is different with a higher resolution camera. The camera I used in my test had a 720p resolution.
Update: I ran a quick test with a higher resolution (10…
The Intel OpenVINO toolkit is the official SDK for the Intel Neural Compute Stick. OpenVINO has support for OpenVX 1.1 API. Take a look at the following page for additional information.
Thank you for reaching out! I was able to compile the model you link with the configuration file you provided. I have seen a similar issue when the system does not have enough memory. How much memory does your system have? I am running …
I don't believe it is a hardware issue with your NCS2 as I am seeing the same results with my NCS2 and OpenVINO on Windows/Linux. If you haven't already, please open the bug report on the Computer Vision forum and paste the link here for r…
I ran a quick test with the sample text_detection_demo on both NCS 1 and NCS 2. The results are very similar on both device, however, the NCS 2 did take a little longer to show the results. Could you tell me which version of the OpenVINO t…
Try inserting the following code on one of the examples as we did in python. I was able to get a successful temperature reading.
unsigned int dataLength;
retCode = mvncGetDeviceOption(deviceHandle, MVNC_THERMAL_STATS, &…
Yolov3 has not been validated on the NCSDK. However, the OpenVINO toolkit just added support for Yolo V3 in the R5 release. I recommend giving OpenVINO a try, you can find the release notes at the following link. https://software.in…
You are correct, I ran into the same issue with the NCSDK v2.10. We have opened a ticket with the development team to take a look.
In the meantime, I recommend using the NCSDK v2.08 as it doesn't seem to have the same issue…
The issue is similar, however, your setup may be a bit different.
What is the output of lsusb when your device is connected?
What version of OpenVINO are you using?
Have you install the VirtualBox Extension Pack and installed on the gu…
Could you share the model you are trying to compile? I would like to try this myself.
Which Neural Compute SDK version are you using? Are you using the Neural Compute Stick 1 or 2?
I have not done any work with pose estimation with the Neural Compute SDK. However, I ran the example code with the pre-trained model included in the OpenVINO toolkit and I am getting about 2.8 FPS on the Intel Neural Compute Stick and a…
The error you are seeing has been discussed in another thread.
The error is due to the model using variable input sizes which is currently not supported on the NCSDK.
Hope this helps!
Thank you for reaching out! Now that you have your TensorFlow model, you will need to convert it to an Intel Movidius Graph file that can be used with the Neural Compute Stick.
The Neural Compute SDK includes the mvNCCompile that is…
We have not validated the NanoPi-m4 with the Neural Compute SDK 1 or 2. The repository above modified the installation for the NCSDK 1, I am not familiar with the changes made.
Currently we only support X86 and Raspberry Pi 3+ runn…
We have not tested the NCSDK 1.12 installation on a docker image. However, we have an installation and configuration with docker guide for the NCSDK 2.x.
Take a look at this link: https://movidius.github.io/ncsdk/docker.html
Hope this h…
Thank you for reaching out. The Neural Compute SDK version 2.10.01.01 was recently released and has support for TensorFlow SSD MobileNet v1/v2 coco networks.
If you are using the OpenVINO toolkit can be used with the Neural Compute Stick…
It's hard to pinpoint what the issue may be without the full error/log. Could you please share the whole error message and the NCSDK version you are installing?
Give the following a try as I had a similar issue with the make examples.…
Thank you for reaching out. Looking at your lsusb output Bus 001 Device 004: ID 03e7:2485, I can see that you are using an Intel Neural Compute Stick 2 (NCS 2). The Neural Compute SDK only has support for the original Neural Com…
I have not tested the NCSDK APIv1 on Windows myself as it is not officially supported. At the moment it is not possible to read the device temperature on OpenVINO, we have added this as a feature request for consideration.
Could you …
Which Neural Compute SDK (NCSDK) are you using? I was able to compile your model into a graph with the NCSDK v2.08.
mvNCCompile mnist_inference.meta -s 12 -in input -on output -o mnist_inference.graph
Also, there is an exa…