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.
6392 Discussions

MobileNetSSD caffe model convert xml not work

賴__世哲
Beginner
511 Views

python3 mo_caffe.py --input_model /home/allen/MobileNetSSD_deploy_Human/MobileNetSSD_deploy_Human.caffemodel --input_proto /home/allen/MobileNetSSD_deploy_Human/MobileNetSSD_deploy.prototxt --data_type FP32

Model Optimizer arguments
        Batch:  1
        Precision of IR:        FP32
        Enable fusing:  True
        Enable gfusing:         True
        Names of input layers:  inherited from the model
        Path to the Input Model:        /home/allen/MobileNetSSD_deploy_Human/MobileNetSSD_deploy_Human.caffemodel
        Input shapes:   inherited from the model
        Log level:      ERROR
        Mean values:    ()
        IR output name:         inherited from the model
        Names of output layers:         inherited from the model
        Path for generated IR:  /opt/intel/computer_vision_sdk_2018.1.265/deployment_tools/model_optimizer
        Reverse input channels:         False
        Scale factor:   None
        Scale values:   ()
        Version:        0.3.75.d6bae621
        Input proto file:       /home/allen/MobileNetSSD_deploy_Human/MobileNetSSD_deploy.prototxt
        Path to CustomLayersMapping.xml:        extensions/front/caffe/CustomLayersMapping.xml
        Path to a mean file:
        Offsets for a mean file:        None
[]

[ SUCCESS ] Generated IR model.
[ SUCCESS ] XML file: /opt/intel/computer_vision_sdk_2018.1.265/deployment_tools/model_optimizer/MobileNetSSD_deploy_Human.xml
[ SUCCESS ] BIN file: /opt/intel/computer_vision_sdk_2018.1.265/deployment_tools/model_optimizer/MobileNetSSD_deploy_Human.bin

 

sudo -E ./object_detection_demo_ssd_async -i bus.mp4 -m /home/allen/MobileNetSSD_deploy_Human/MobileNetSSD_deploy_Human.xml -d GPU
[sudo] password for allen:
InferenceEngine:
        API version ............ 1.0
        Build .................. 10478
[ INFO ] Parsing input parameters
[ INFO ] Reading input
[ INFO ] Loading plugin

        API version ............ 0.1
        Build .................. ci-main-03313
        Description ....... clDNNPlugin
[ INFO ] Loading network files
[ INFO ] Batch size is forced to  1.
[ INFO ] Checking that the inputs are as the sample expects
[ INFO ] Checking that the outputs are as the sample expects
[ INFO ] Loading model to the plugin
[ INFO ] Start inferenceOnly 0 proposals found

Only 0 proposals found

Only 0 proposals found
Only 0 proposals found
Only 0 proposals found
Only 0 proposals found

 

detection is not work

 

0 Kudos
2 Replies
Jeffrey_M_Intel1
Employee
511 Views

You may need to add mean and scale values.  This command line works for the mobilenet-ssd downloaded by the model downloader utility:

mo.py --input_model mobilenet-ssd.caffemodel  --mean_values [123.68,116.779,103.939] --scale 255  --data_type FP32

 

0 Kudos
賴__世哲
Beginner
511 Views

Jeffrey M. (Intel) wrote:

You may need to add mean and scale values.  This command line works for the mobilenet-ssd downloaded by the model downloader utility:

mo.py --input_model mobilenet-ssd.caffemodel  --mean_values [123.68,116.779,103.939] --scale 255  --data_type FP32

 

 

thank you very much, it's work !

0 Kudos
Reply