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.

Inference Engine Error with Yolov3 model

SC_Huang
Beginner
499 Views

We have a yolov3 model,

using model optimizer with command

python mo_tf.py --input_model C:\Users\Documents\Intel\OpenVINO\yolo_v3.pb --tensorflow_use_custom_operations_config extensions\front\tf\yolo_v3.json --input_shape=[1,416,416,3] --log_level=DEBUG --data_type=FP16 --output_dir C:\Users\Documents\Customer\Telexper\yolo3_caffe

and successfully generate IR file,

but when excute object_detection_demo_yolov3_async.exe with the IR,

Error occure 

object_detection_demo_yolov3_async.exe -m C:\Users\Documents\Customer\Telexper\yolo3_caffe\yolo_v3.xml -i C:\Users\Documents\Customer\Telexper\ObjectDetection-YOLO\run.mp4 -d GPU
InferenceEngine:
        API version ............ 1.4
        Build .................. 19154
[ INFO ] Parsing input parameters
[ INFO ] Reading input
[ INFO ] Loading plugin

        API version ............ 1.5
        Build .................. 19154
        Description ....... clDNNPlugin
[ INFO ] Loading network files
[ INFO ] Batch size is forced to  1.
[ INFO ] Checking that the inputs are as the demo expects
[ INFO ] Checking that the outputs are as the demo expects
[ INFO ] Loading model to the plugin
17 errors generated.
41 errors generated.
41 errors generated.
37 errors generated.
[ ERROR ] program creation failed: Program build failed:
13:7118:29: error: implicit declaration of function 'intel_sub_group_block_read_us8' is invalid in OpenCL
header_with_defs_gpu.h:299:39: note: expanded from macro 'as_half8'
13:7118:29: note: did you mean 'in

Why the sample app got error like that?

0 Kudos
3 Replies
Shubha_R_Intel
Employee
499 Views

Dear SC Huang:

So you're using a Caffe Yolo3 model instead of a tensorflow one ? Please give the URL from which you obtained this caffe model.

Thanks for using OpenVino !

Shubha

0 Kudos
SC_Huang
Beginner
499 Views

Shubha R. (Intel) wrote:

Dear SC Huang:

So you're using a Caffe Yolo3 model instead of a tensorflow one ? Please give the URL from which you obtained this caffe model.

Thanks for using OpenVino !

Shubha

https://drive.google.com/open?id=1HsLIkno6ueHRdQmYewF4RCnOC4qdnGQf

Yolov3.cfg

https://drive.google.com/open?id=1G4PPOlWLNCAHwz_ztMTCQoANF5fUXATi

Yolov3.weights

0 Kudos
Shubha_R_Intel
Employee
499 Views

Dear SC Huang,

I think you misunderstood my question. The *.cfg and *.weights won't help me to debug your issue but the frozen *.pb would.

Have you tried 2019 R1 ? Many problems are magically fixed in the new release. Would you kindly give it a go ?

Thanks for using OpenVino !

Shubha

0 Kudos
Reply