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.

getting error when i run openVINO demo application(on ubuntu ) with "-d HDDL" option on UP2 board

BK__Venu
Beginner
1,396 Views

Hi All,

I am running a openVINO demo application on UP2 board (UPS-APLC2-A20-0432) installed UBUNTU on it, with the command "./demo_squeezenet_download_convert_run.sh -d HDDL"

i have followed all the installation step given in docs. but getting following error. can you help me to resolve this issue.

 

Preparing output blobs
[ INFO ] Loading model to the plugin
[12:02:39.9233][10441]I[ServiceStarter.cpp:40] Info: Waiting for HDDL Service getting ready ...
[12:02:39.9235][10441]I[ServiceStarter.cpp:45] Info: Found HDDL Service is running.
[HDDLPlugin] [12:02:39.9237][10441]I[ConfigParser.cpp:176] Config file '/opt/intel/openvino_2019.1.094/deployment_tools/inference_engine/external/hddl/config/hddl_api.config' has been loaded
Hddl api version:2.2
[HDDLPlugin] [12:02:39.9238][10441]I[HddlClient.cpp:259] Info: Create Dispatcher2.
[HDDLPlugin] [12:02:39.9243][10441]I[HddlClient.cpp:270] Info: RegisterClient HDDLPlugin.
[HDDLPlugin] [12:02:39.9246][10445]I[Dispatcher2.cpp:148] Info: SenderRoutine starts.
Client Id:10
[HDDLPlugin] [12:02:39.9268][10446]I[Dispatcher2.cpp:235] Info: Other side of pipe is closed, shut down socket.
[HDDLPlugin] [12:02:39.9270][10441]I[Dispatcher2.cpp:81] Info: Client dispatcher exit.
[HDDLPlugin] [12:02:39.9273][10441]I[HddlClient.cpp:203] Info: Hddl client unregistered.
[ ERROR ] no devices found
Error on or near line 241; exiting with status 1

 

Thanks and regads

Venu

0 Kudos
4 Replies
JesusE_Intel
Moderator
1,396 Views

Hi Venu,

I am looking at the Up Square specifications from AAEON and I don't see a Intel Myriad VPU included. Have you added a device with an Intel Myriad VPU such as the Neural Compute Stick 2? If so, could you try running the demo with -d MYRIAD.

You can also run the demo on the CPU without specifying a device with the -d parameter.

Regards,

Jesus

0 Kudos
BK__Venu
Beginner
1,396 Views

Hi Jesus,

I Have added a "UP AI Core X Neural Accelerator" which has 1 VPU to the UP2 board through mPci port. which need "-d HDDL" option

I tried CPU and -d MYRIAD(Neural Compute Stick) option it is working fine.

OS is  UBUNTU 16.04 installed with intel distribution for openVINO 2019 R1. and installed i2c driver as mentioned in openVINO  installation guide.

Thanks and regards

Venu

 

 

 

0 Kudos
JesusE_Intel
Moderator
1,396 Views

Hi Venu,

I went through the configuration guide to setup the Intel Vision Accelerator Design on Linux and I was able to run the sample without any issues. I noticed that your OpenVINO Toolkit version is not the latest one. Could you try upgrading to the latest OpenVINO Toolkit and see if that solves your issue? 

[HDDLPlugin] [12:02:39.9237][10441]I[ConfigParser.cpp:176] Config file '/opt/intel/openvino_2019.1.094/deployment_tools/inference_engine/external/hddl/config/hddl_api.config' has been loaded
Hddl api version:2.2

The latest release should show openvino_2019.1.144.

Regards,

Jesus

0 Kudos
Omar-AE
Beginner
1,387 Views

I have been having this issue since around a week and still have no idea how to solve it.

Here is the last part of the output I get when I run any one of the demos by running:
sudo -E ./demo_squeezenet_download_convert_run.sh -d HDDL

Run Inference Engine classification sample

Run ./classification_sample_async -d HDDL -i /opt/intel/openvino_2020.2.120/deployment_tools/demo/car.png -m /home/nvr/openvino_models/ir/public/squeezenet1.1/FP16/squeezenet1.1.xml

[ INFO ] InferenceEngine: 
	API version ............ 2.1
	Build .................. 42025
	Description ....... API
[ INFO ] Parsing input parameters
[ INFO ] Parsing input parameters
[ INFO ] Files were added: 1
[ INFO ]     /opt/intel/openvino_2020.2.120/deployment_tools/demo/car.png
[ INFO ] Creating Inference Engine
	HDDL
	HDDLPlugin version ......... 2.1
	Build ........... custom_releases/2020/2_d8830cd2bfe6199444299be1d92b281e5459f195

[ INFO ] Loading network files
[ INFO ] Preparing input blobs
[ WARNING ] Image is resized from (787, 259) to (227, 227)
[ INFO ] Batch size is 1
[ INFO ] Loading model to the device
[14:12:30.8923][24788]I[main.cpp:243] ## HDDL_INSTALL_DIR: /opt/intel/openvino_2020.2.120/deployment_tools/inference_engine/external/hddl
[14:12:30.8927][24788]I[main.cpp:245] Config file '/opt/intel/openvino_2020.2.120/deployment_tools/inference_engine/external/hddl/config/hddl_service.config' has been loaded
[14:12:30.8947][24788]I[FileHelper.cpp:272] Set file:/var/tmp/hddl_service_alive.mutex owner: user-'no_change', group-'users', mode-'0660'
[14:12:30.8949][24788]I[FileHelper.cpp:272] Set file:/var/tmp/hddl_service_ready.mutex owner: user-'no_change', group-'users', mode-'0660'
[14:12:30.8951][24788]I[FileHelper.cpp:272] Set file:/var/tmp/hddl_start_exit.mutex owner: user-'no_change', group-'users', mode-'0660'
[14:12:30.8994][24788]I[AutobootStarter.cpp:156] Info: No running autoboot process. Start autoboot daemon...
[14:12:30.9794][24792]I[FileHelper.cpp:272] Set file:/var/tmp/hddl_autoboot_alive.mutex owner: user-'no_change', group-'users', mode-'0660'
[14:12:30.9802][24792]I[FileHelper.cpp:272] Set file:/var/tmp/hddl_autoboot_ready.mutex owner: user-'no_change', group-'users', mode-'0660'
[14:12:30.9807][24792]I[FileHelper.cpp:272] Set file:/var/tmp/hddl_autoboot_start_exit.mutex owner: user-'no_change', group-'users', mode-'0660'
[14:12:30.9812][24792]I[FileHelper.cpp:272] Set file:/tmp/hddl_autoboot_device.map owner: user-'no_change', group-'users', mode-'0660'
[14:12:30.9838][24792]I[AutoBoot.cpp:308] [Firmware Config] deviceName=default deviceNum=0 firmwarePath=/opt/intel/openvino_2020.2.120/deployment_tools/inference_engine/external/hddl/lib/mvnc/usb-ma2x8x.mvcmd
[14:12:51.3108][24788]I[AutobootStarter.cpp:85] Info: Autoboot is running.
[14:12:51.3492][24788]I[TaskSchedulerFactory.cpp:45] Info: ## TaskSchedulerFactory ## Created Polling Task-Scheduler.
[14:12:51.3514][24788]I[FileHelper.cpp:272] Set file:/var/tmp/hddl_snapshot.sock owner: user-'no_change', group-'users', mode-'0660'
[14:12:51.3557][24788]I[FileHelper.cpp:272] Set file:/var/tmp/hddl_service.sock owner: user-'no_change', group-'users', mode-'0660'
[14:12:51.3564][24788]I[MessageDispatcher.cpp:87] Message Dispatcher initialization finished
[14:12:51.3567][24788]I[main.cpp:103] SERVICE IS READY ...
[14:12:51.4492][24847]I[ClientManager.cpp:159] client(id:1) registered: clientName=HDDLPlugin socket=2
[14:12:51.4813][24847]I[ClientManager.cpp:189] client(id:1) unregistered: clientName=HDDLPlugin socket=2
[ ERROR ] no devices found
Error on or near line 217; exiting with status 1

 

I tried two mPCIe boards from two different vendors: vega-300 and EDL-mPCIe-MA2485

when I run the python script hello_query_device.py, both the CPU and HDDL devices appear:

/opt/intel/openvino_2020.2.120/deployment_tools/inference_engine/samples/python/hello_query_device$ python3 hello_query_device.py 
Available devices:
	Device: CPU
	Metrics:
		AVAILABLE_DEVICES: 
		SUPPORTED_METRICS: AVAILABLE_DEVICES, SUPPORTED_METRICS, FULL_DEVICE_NAME, OPTIMIZATION_CAPABILITIES, SUPPORTED_CONFIG_KEYS, RANGE_FOR_ASYNC_INFER_REQUESTS, RANGE_FOR_STREAMS
		FULL_DEVICE_NAME:       Intel(R) Celeron(R) CPU  J1900  @ 1.99GHz
		OPTIMIZATION_CAPABILITIES: FP32, INT8, BIN
		SUPPORTED_CONFIG_KEYS: CPU_BIND_THREAD, CPU_THREADS_NUM, CPU_THROUGHPUT_STREAMS, DUMP_EXEC_GRAPH_AS_DOT, DYN_BATCH_ENABLED, DYN_BATCH_LIMIT, EXCLUSIVE_ASYNC_REQUESTS, PERF_COUNT
		RANGE_FOR_ASYNC_INFER_REQUESTS: 1, 1, 1
		RANGE_FOR_STREAMS: 1, 4

	Default values for device configuration keys:
		CPU_BIND_THREAD: YES
		CPU_THREADS_NUM: 0
		CPU_THROUGHPUT_STREAMS: 1
		DUMP_EXEC_GRAPH_AS_DOT: 
		DYN_BATCH_ENABLED: NO
		DYN_BATCH_LIMIT: 0
		EXCLUSIVE_ASYNC_REQUESTS: NO
		PERF_COUNT: NO
	Device: HDDL
	Metrics:
		AVAILABLE_DEVICES: 
		SUPPORTED_METRICS: AVAILABLE_DEVICES, SUPPORTED_METRICS, SUPPORTED_CONFIG_KEYS, FULL_DEVICE_NAME, OPTIMIZATION_CAPABILITIES, RANGE_FOR_ASYNC_INFER_REQUESTS, VPU_HDDL_DEVICE_NUM, VPU_HDDL_DEVICE_NAME, VPU_HDDL_DEVICE_THERMAL, VPU_HDDL_DEVICE_ID, VPU_HDDL_DEVICE_SUBCLASS, VPU_HDDL_DEVICE_MEMORY_TOTAL, VPU_HDDL_DEVICE_MEMORY_USED, VPU_HDDL_DEVICE_UTILIZATION, VPU_HDDL_DEVICE_TAG, VPU_HDDL_STREAM_ID
		SUPPORTED_CONFIG_KEYS: PERF_COUNT, VPU_INPUT_NORM, VPU_INPUT_BIAS, VPU_HDDL_GRAPH_TAG, VPU_HDDL_STREAM_ID, VPU_HDDL_DEVICE_TAG, VPU_HDDL_BIND_DEVICE, VPU_HDDL_RUNTIME_PRIORITY, VPU_HDDL_USE_SGAD, VPU_COPY_OPTIMIZATION, LOG_LEVEL, VPU_IGNORE_UNKNOWN_LAYERS, VPU_HW_STAGES_OPTIMIZATION, VPU_NONE_LAYERS, VPU_NUMBER_OF_SHAVES, VPU_NUMBER_OF_CMX_SLICES, VPU_HW_INJECT_STAGES, VPU_HW_POOL_CONV_MERGE, VPU_HW_STAGES_OPTIMIZATION, EXCLUSIVE_ASYNC_REQUESTS
		FULL_DEVICE_NAME: Intel Vision Accelerator Design with Intel Movidius VPUs
		OPTIMIZATION_CAPABILITIES: FP16
		RANGE_FOR_ASYNC_INFER_REQUESTS: 0, 2000, 1
		VPU_HDDL_DEVICE_NUM: 0
		VPU_HDDL_DEVICE_NAME: 
		VPU_HDDL_DEVICE_THERMAL: 
		VPU_HDDL_DEVICE_ID: 
		VPU_HDDL_DEVICE_SUBCLASS: 
		VPU_HDDL_DEVICE_MEMORY_TOTAL: 
		VPU_HDDL_DEVICE_MEMORY_USED: 
		VPU_HDDL_DEVICE_UTILIZATION: 
		VPU_HDDL_DEVICE_TAG: 
		VPU_HDDL_STREAM_ID: 

	Default values for device configuration keys:
		PERF_COUNT: 
		VPU_INPUT_NORM: 
		VPU_INPUT_BIAS: 
		VPU_HDDL_GRAPH_TAG: 
		VPU_HDDL_STREAM_ID: 
		VPU_HDDL_DEVICE_TAG: 
		VPU_HDDL_BIND_DEVICE: 
		VPU_HDDL_RUNTIME_PRIORITY: 
		VPU_HDDL_USE_SGAD: 
		VPU_COPY_OPTIMIZATION: 
		LOG_LEVEL: 
		VPU_IGNORE_UNKNOWN_LAYERS: 
		VPU_HW_STAGES_OPTIMIZATION: 
		VPU_NONE_LAYERS: 
		VPU_NUMBER_OF_SHAVES: 
		VPU_NUMBER_OF_CMX_SLICES: 
		VPU_HW_INJECT_STAGES: 
		VPU_HW_POOL_CONV_MERGE: 
		VPU_HW_STAGES_OPTIMIZATION: 
		EXCLUSIVE_ASYNC_REQUESTS: 

 

When I run lsusb, the mpcie does not appear. I have the mpcie connected to the mpcie port on the motherboard.

The demo runs successfully on the CPU (intel J1900)

I am using ubuntu 18.04

One last note: I was able to run the demo successfully on the HDDL only once, and immediately after that, I ran the same command and the same error above came back.

0 Kudos
Reply