Stack Overflow
Stack Overflow

Questions tagged [movidius]

Movidius are usb sticks to accelerate the execution of neuronal networks.

21 questions
4
votes
0 answers

How to change the input shape of an existing tensorflow model (.pb)

I want to turn a preexisting tensorflow graph into a graph that can be deployed on the Movidius Neural Compute stick. When I use the command mvNCCompile (from NCSDK), following Error occurs: [Error 5] Toolkit Error: Stage Details Not Supported:…
klopfer384
  • 41
  • 4
2
votes
1 answer

Run multiple networks on the same Intel Neural Compute Stick 2 (NCS2/MYRIAD)?

I want to load and run multiple networks on the same NCS2: a one-class object detection network (like a person detector), and a network for some recognition on that detection (like gesture recognition). I tried to load the networks on one NCS2…
Fardo
  • 107
  • 1
  • 1
  • 9
2
votes
1 answer

OpenVino Model Optimizer Error when converting TensorFlow model

I have created a custom image classification .pb model file using the python scripts in the TensorFlow for Poets 2 repo (https://github.com/googlecodelabs/tensorflow-for-poets-2). I tried converting it to Intermediate Representation using the…
Gino
  • 21
  • 4
2
votes
1 answer

openvino crashes after running inference some seconds in raspberry pi 4

I tried to use Intel Neural Compute Stick 2 as an inference engine for my smart car. I installed l_openvino_toolkit_runtime_raspbian_p_2019.2.242.tgz followed by this link, and run the code for testing. Everything was fine at the beginning of 10 -…
Tony Teng
  • 105
  • 8
1
vote
2 answers

How to deploy OpenVINO IR model to Intel Movidius Myriadx VPU

I searched a while and could not find any documents about deploying the OpenVINO IR model directly to Intel's MyriadX VPU. My understanding is they both come from Intel, there should be a way to do this. What can I try in order to solve this?
Franva
  • 6,565
  • 23
  • 79
  • 144
1
vote
1 answer

Cannot infer on Movidius (NCS2) using OpenVINO Workbench through Docker: Drivers setup failed?

I am trying to run some inferences using the OpenVINO Workbench Docker image https://hub.docker.com/r/openvino/workbench . Everything works well using my CPU as targeted device (Configuration -> Select Environment). But I get the following error…
Michael Benguigui
  • 53
  • 1
  • 5
1
vote
1 answer

How to retrain a detection model and quantize it for Intel Movidius?

I want to retrain an existing object detection model with a new image dataset and quantize it for Intel Movidius. Is there any working procedure to do this? I have successfully retrained the model but failing to quantize it. I have followed the…
ksohan
  • 1,165
  • 2
  • 9
  • 23
1
vote
1 answer

OpenVINO + HDDL plugin - Cannot run openvino samples - "HDDL hardware initialization failed"

I'm trying to get OpenVINO samples working on an mPCIe Myriad X card (with 2 MA2485 chips). My goal is to get the samples working using the HDDL plugin, as from my understanding it should allow for working with multiple chips in parallel. Using…
nadavvadan
  • 3,930
  • 1
  • 17
  • 29
0
votes
1 answer

How to set up Raspberry Pi Buster and Intel NCS2 and OpenVINO with OpenCV trackers

Is there a definitive set of instructions to implement OpenCV trackers with OpenVINO and the now-obsolete NCS2 on a RPi 4b - Buster? My understanding that the last OpenVINO to support the NCS2 was v2020.3. I attempted to cross-compile…
user773881
  • 845
  • 1
  • 8
  • 10
0
votes
1 answer

Inference on openvino model returns only scores

My task is to perform inference for face detection using Intel Movidius and Raspberry Pi. The error is that the model only returns "Scores" -> (1, 3000, 2) and not "Boxes". Steps: On my local machine, I trained several models(mb1-ssd, mb1-ssd-lite,…
pinbu
  • 5
  • 2
0
votes
1 answer

openvino human pose estimation 0007

I am working with openvinotoolkit and I am trying to inference the model human-pose-estimation-0007 and that works fine on neural stick 2. Now I am looking for the original human-pose-estimation-0007 weights o repository (Multi-person 2D pose…
ssgakhal
  • 408
  • 3
  • 15
0
votes
1 answer

How to apply a model from the Model Zoo which has bigger input size than the OpenCV OAK-D's resolution(FHD 1920x1080)

Just wondering if I choose a model from the Model Zoo which has bigger input size than the OPEN-CV OAK-D's resolution(FHD 1920x1080) it errors out. To be more specific, I am trying to deploy a model which can be the fastseg-small or…
Franva
  • 6,565
  • 23
  • 79
  • 144
0
votes
1 answer

Openvino movidius cant read IP camera

id like to make my movidius NCS1 read a IP camera. this is my code: import cv2 #print("Before URL") cap = cv2.VideoCapture('rtsp://admin:sphbr7410@192.168.240.151:554/cam/realmonitor?channel=1&subtype=0') #print("After URL") while True: …
Jasar Orion
  • 626
  • 7
  • 26
0
votes
1 answer

how to deploy a model trained on TF2 Keras on Movidius Myriad 2 (NCSDK 2.05.00.02)

I try to optimize my model using 'MvNCCompile' but it doesn't accept my frozen TF2 graph. 'Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.'. Can I somehow convert my TF2 (keras) model to TF1 graph…
Daaan
  • 51
  • 3
0
votes
0 answers

How can i find frozen_inference_graph.pb input and output node?

i have already trained a model by ssd inception v2 model and use "export_inference_graph.py" to generated the frozen_inference_graph.pb i tried to use below command to generated the model then try to use mvNCCompiler to convert it to movidius…
ChiHang_Chan
  • 1
1
2