Community
cancel
Showing results for 
Search instead for 
Did you mean: 
idata
Community Manager
455 Views

dispatcherEventReceive() Read failed -4 with C API

I hit the error "dispatcherEventReceive() Read failed -4" when programming with C API.

 

But there is no such issue when programming with Python API.

 

I use the same graph, the save test image, the same Ubuntu 16.04 host.

 

Any idea about it?

 

//Error log with C API:

 

Logging level set to: 0

 

D: [ 0] ncDeviceCreate:307 ncDeviceCreate index 0

 

Found device No 0

 

D: [ 0] ncDeviceOpen:501 File path /usr/local/lib/mvnc/MvNCAPI-ma2450.mvcmd

 

I: [ 0] ncDeviceOpen:507 ncDeviceOpen() XLinkBootRemote returned success 0

 

I: [ 0] ncDeviceOpen:536 XLinkConnect done - link Id 0

 

D: [ 0] ncDeviceOpen:550 done

 

I: [ 0] ncDeviceOpen:552 Booted 1.1.1-ma2450 -> VSC

 

I: [ 0] getDevAttributes:373 Device attributes

 

I: [ 0] getDevAttributes:376 Device FW version: 2.4.2450.f0

 

I: [ 0] getDevAttributes:378 mvTensorVersion 2.4

 

I: [ 0] getDevAttributes:379 Maximum graphs: 10

 

I: [ 0] getDevAttributes:380 Maximum fifos: 20

 

I: [ 0] getDevAttributes:382 Maximum graph option class: 1

 

I: [ 0] getDevAttributes:384 Maximum device option class: 1

 

I: [ 0] getDevAttributes:385 Device memory capacity: 522073264

 

Successfully opened device 0

 

Successfully loaded graph file, size is: 31547156

 

I: [ 0] ncGraphAllocate:923 Starting Graph allocation sequence

 

I: [ 0] ncGraphAllocate:988 Sent graph

 

D: [ 0] ncGraphAllocate:1013 Graph Status 0 rc 0

 

D: [ 0] ncGraphAllocate:1059 Input tensor w 416 h 416 c 3 n 1 totalSize 1038336 wstide 6 hstride 2496 cstride 2 layout 0

 

D: [ 0] ncGraphAllocate:1072 output tensor w 13 h 13 c 40 n 1 totalSize 13520 wstide 80 hstride 1040 cstride 2 layout 0

 

I: [ 0] ncGraphAllocate:1126 Graph allocation completed successfully

 

I: [ 0] ncFifoCreate:2126 Init fifo

 

I: [ 0] ncFifoAllocate:2321 Creating fifo

 

I: [ 0] ncFifoCreate:2126 Init fifo

 

I: [ 0] ncFifoAllocate:2321 Creating fifo

 

Successfully allocated graph

 

enqueueImg 1

 

preprocess_image 1

 

preprocess_image 2 416 555, 0.693333

 

preprocess_image 3 69 0 416 416

 

preprocess_image 4 416 416

 

enqueueImg 2

 

enqueueImg 3

 

enqueueImg 3 519168

 

enqueueImg 4 416 416

 

tensor preprocessed

 

D: [ 0] ncFifoWriteElem:2592 No layout conversion is needed 0

 

D: [ 0] convertDataTypeAndLayout:170 src data type 1 dst data type 0

 

D: [ 0] convertDataTypeAndLayout:172 SRC: w 416 h 416 c 3 w_s 12 h_s 4992 c_s 4

 

D: [ 0] convertDataTypeAndLayout:174 DST: w 416 h 416 c 3 w_s 6 h_s 2496 c_s 2

 

D: [ 0] ncFifoWriteElem:2617 write count 0 num_elements 2 userparam (nil)

 

I: [ 0] ncGraphQueueInference:3048 trigger start

 

I: [ 0] ncGraphQueueInference:3145 trigger end

 

tensor loaded

 

E: [ 0] dispatcherEventReceive:200 dispatcherEventReceive() Read failed -4

 

Normal log with python API:

 

D: [ 0] ncDeviceCreate:307 ncDeviceCreate index 0

 

D: [ 0] ncDeviceCreate:307 ncDeviceCreate index 1

 

graph file graph

 

D: [ 0] ncDeviceOpen:501 File path /usr/local/lib/mvnc/MvNCAPI-ma2450.mvcmd

 

I: [ 0] ncDeviceOpen:507 ncDeviceOpen() XLinkBootRemote returned success 0

 

I: [ 0] ncDeviceOpen:536 XLinkConnect done - link Id 0

 

D: [ 0] ncDeviceOpen:550 done

 

I: [ 0] ncDeviceOpen:552 Booted 1.1.1-ma2450 -> VSC

 

I: [ 0] getDevAttributes:373 Device attributes

 

I: [ 0] getDevAttributes:376 Device FW version: 2.4.2450.f0

 

I: [ 0] getDevAttributes:378 mvTensorVersion 2.4

 

I: [ 0] getDevAttributes:379 Maximum graphs: 10

 

I: [ 0] getDevAttributes:380 Maximum fifos: 20

 

I: [ 0] getDevAttributes:382 Maximum graph option class: 1

 

I: [ 0] getDevAttributes:384 Maximum device option class: 1

 

I: [ 0] getDevAttributes:385 Device memory capacity: 522073264

 

I: [ 0] ncGraphAllocate:923 Starting Graph allocation sequence

 

I: [ 0] ncGraphAllocate:988 Sent graph

 

D: [ 0] ncGraphAllocate:1013 Graph Status 0 rc 0

 

D: [ 0] ncGraphAllocate:1059 Input tensor w 416 h 416 c 3 n 1 totalSize 1038336 wstide 6 hstride 2496 cstride 2 layout 0

 

D: [ 0] ncGraphAllocate:1072 output tensor w 13 h 13 c 40 n 1 totalSize 13520 wstide 80 hstride 1040 cstride 2 layout 0

 

I: [ 0] ncGraphAllocate:1126 Graph allocation completed successfully

 

I: [ 0] ncFifoCreate:2126 Init fifo

 

I: [ 0] ncFifoAllocate:2321 Creating fifo

 

I: [ 0] ncFifoCreate:2126 Init fifo

 

I: [ 0] ncFifoAllocate:2321 Creating fifo

 

/usr/local/lib/python3.5/dist-packages/skimage/transform/_warps.py:84: UserWarning: The default mode, 'constant', will be changed to 'reflect' in skimage 0.15.

 

warn("The default mode, 'constant', will be changed to 'reflect' in "

 

D: [ 0] ncFifoWriteElem:2592 No layout conversion is needed 0

 

D: [ 0] convertDataTypeAndLayout:170 src data type 1 dst data type 0

 

D: [ 0] convertDataTypeAndLayout:172 SRC: w 416 h 416 c 3 w_s 12 h_s 4992 c_s 4

 

D: [ 0] convertDataTypeAndLayout:174 DST: w 416 h 416 c 3 w_s 6 h_s 2496 c_s 2

 

D: [ 0] ncFifoWriteElem:2617 write count 0 num_elements 2 userparam 0x7ff100f16098

 

I: [ 0] ncGraphQueueInference:3048 trigger start

 

I: [ 0] ncGraphQueueInference:3145 trigger end

 

D: [ 0] ncFifoReadElem:2686 No layout conversion is needed 0

 

D: [ 0] convertDataTypeAndLayout:170 src data type 0 dst data type 1

 

D: [ 0] convertDataTypeAndLayout:172 SRC: w 13 h 13 c 40 w_s 80 h_s 1040 c_s 2

 

D: [ 0] convertDataTypeAndLayout:174 DST: w 13 h 13 c 40 w_s 160 h_s 2080 c_s 4

 

D: [ 0] ncFifoReadElem:2714 num_elements 2 userparam 0x7ff100f16340 output length 27040

 

/usr/lib/python3.5/site-packages/mvnc/mvncapi.py:418: DeprecationWarning: The binary mode of fromstring is deprecated, as it behaves surprisingly on unicode inputs. Use frombuffer instead

 

tensor = numpy.fromstring(tensor.raw, dtype=numpy.float32)

 

c=40 h=13 w=13 classes=3 imgw=800 imgh=600 thresh=0.200000 nms=0.400000 blockwd=13

 

0.449785 0.508008 0.055721 0.115349

 

0.802951 0.526414 0.073199 0.115363

 

-0.030884 0.522461 0.318359 0.267334 0.313965 0.334717 0.318359 0.317383 0.304443 0.322998 0.288574 0.300781 0.313232 -0.459961 0.810547 0.841309 0.649414 0.603027 0.588867 0.562012 0.558105 0.532227 0.556152 0.573730 0.522461 0.417969 -0.400635 0.487549 0.458984 0.291260 0.230103 0.169922 0.155762 0.187744 0.197510 0.162231 0.131226 0.008354 -0.056793 -0.073853 0.041870 -0.049011 -0.149780 -0.264404 -0.281738 -0.280518 -0.208252 -0.206177 -0.214111 -0.143188 -0.151611 -0.057312 0.820801 -0.487549 -0.297363 0.107422 0.139282 -0.102783 -0.603516 -0.299561 -0.073303 -0.074463 -0.571777 -0.377197 0.224854 2.814453 -1.152344 -0.597168 0.710449 1.921875 1.272461 -0.640625 -0.268311 0.771973 1.841797 -0.597168 -0.852539 0.687500 3.070312 -2.197266 -1.197266 0.683594 2.878906 1.712891 -1.206055 -0.709961 1.184570 3.085938 -0.247803 -1.708008 0.166260 1.620117 -1.049805 -0.338135 0.225098 1.593750 1.181641 -0.159912 -0.105408 0.623047 2

 

total time is " milliseconds 251.5

 

I: [ 0] ncDeviceClose:742 closing device
0 Kudos
2 Replies
idata
Community Manager
120 Views

Hi @Fei

 

Which Neural Compute SDK version are you using? Could you provide me your model and code to replicate your issue?

 

Regards,

 

Jesus
idata
Community Manager
120 Views

Thank you for feedback, Jesus.

 

I finally worked it out.

 

The failure is related to the format of input image.

 

If I remember correctly, CV_32FC3 is the working one.
Reply