detectnet-camera fails

Autonomous Machines Jetson & Embedded Systems Jetson Nano
1

I successfully downloaded and compiled the deep vision tutorial from here:

https://github.com/dusty-nv/jetson-inference/blob/master/docs/building-repo-2.md

i am using the raspberry pi camera and the hardware works ok

./detectnet-camera facenet
detectnet-camera
  args (2):  0 [./detectnet-camera]  1 [facenet]  

[gstreamer] initialized gstreamer, version 1.14.1.0
[gstreamer] gstCamera attempting to initialize with GST_SOURCE_NVCAMERA
[gstreamer] gstCamera pipeline string:
nvcamerasrc fpsRange="30.0 30.0" ! video/x-raw(memory:NVMM), width=(int)1280, height=(int)720, format=(string)NV12 ! nvvidconv flip-method=2 ! video/x-raw ! appsink name=mysink
[gstreamer] gstCamera failed to create pipeline
[gstreamer]    (no element "nvcamerasrc")
[gstreamer] failed to init gstCamera (GST_SOURCE_NVCAMERA)
[gstreamer] gstCamera attempting to initialize with GST_SOURCE_NVARGUS
[gstreamer] gstCamera pipeline string:
nvarguscamerasrc ! video/x-raw(memory:NVMM), width=(int)1280, height=(int)720, framerate=30/1, format=(string)NV12 ! nvvidconv flip-method=2 ! video/x-raw ! appsink name=mysink
[gstreamer] gstCamera successfully initialized with GST_SOURCE_NVARGUS

detectnet-camera:  successfully initialized video device
    width:  1280
   height:  720
    depth:  12 (bpp)

detectNet -- loading detection network model from:
          -- prototxt     networks/facenet-120/deploy.prototxt
          -- model        networks/facenet-120/snapshot_iter_24000.caffemodel
          -- input_blob   'data'
          -- output_cvg   'coverage'
          -- output_bbox  'bboxes'
          -- mean_pixel   0.000000
          -- class_labels networks/facenet-120/class_labels.txt
          -- threshold    0.500000
          -- batch_size   2

[TRT]  TensorRT version 5.0.6
[TRT]  detected model format - caffe  (extension '.caffemodel')
[TRT]  desired precision specified for GPU: FASTEST
[TRT]  requested fasted precision for device GPU without providing valid calibrator, disabling INT8
[TRT]  native precisions detected for GPU:  FP32, FP16
[TRT]  selecting fastest native precision for GPU:  FP16
[TRT]  attempting to open engine cache file networks/facenet-120/snapshot_iter_24000.caffemodel.2.1.GPU.FP16.engine
[TRT]  cache file not found, profiling network model on device GPU
[TRT]  device GPU, loading networks/facenet-120/deploy.prototxt networks/facenet-120/snapshot_iter_24000.caffemodel
[TRT]  retrieved Output tensor "coverage":  1x28x28
[TRT]  retrieved Output tensor "bboxes":  4x28x28
[TRT]  retrieved Input tensor "data":  3x450x450
[TRT]  device GPU, configuring CUDA engine
[TRT]  device GPU, building FP16:  ON
[TRT]  device GPU, building INT8:  OFF
[TRT]  device GPU, building CUDA engine (this may take a few minutes the first time a network is loaded)

after about 15 minutes it then puts up a window and captures two frames and then freezes.
And in terminal i see lots of this:

detectnet-camera:  failed to capture frame
detectnet-camera:  failed to convert from NV12 to RGBA
detectNet::Detect( 0x(nil), 1280, 720 ) -> invalid parameters
[cuda]   cudaNormalizeRGBA((float4*)imgRGBA, make_float2(0.0f, 255.0f), (float4*)imgRGBA, make_float2(0.0f, 1.0f), camera->GetWidth(), camera->GetHeight())
[cuda]      invalid device pointer (error 17) (hex 0x11)
[cuda]      /home/stefan/jetson-inference/detectnet-camera/detectnet-camera.cpp:247
2

I got it to work at 10 fps by running ./jetson_clocks
and making sure the camera was right side up and my face was not too close or off angle

However, face detection is quite poor.

3

Hi,

You can customize a model with your own dataset.
Here is our tutorial for your reference:
[url]https://github.com/dusty-nv/jetson-inference/blob/master/docs/detectnet-training.md[/url]

Thanks.