Error running object recognition sample from tegra multimedia api

I followed instructions as on the documentation for jetpack 3.2.

nvidia@tegra-ubuntu:~/tegra_multimedia_api/samples/11_camera_object_identification$ ./camera_caffe -width 1920 -height 1080 -lib opencv_consumer_lib/libopen
cv_consumer.so -model $HOME/caffe/models/bvlc_reference_caffenet/deploy.prototxt -trained $HOME/caffe/models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel -mean $HOME/caffe/data/ilsvrc12/imagenet_mean.binaryproto -label $HOME/caffe/data/ilsvrc12/synset_words.txt
opencv_handler_open is called
opencv_set_config 0
Image width 1920
opencv_set_config 1
Image height 1080
opencv_set_config 2
CAFFE model file : 0x6548a0
opencv_set_config 3
CAFFE trained file : 0x63a4d0
opencv_set_config 4
CAFFE mean file : 0x63a560
opencv_set_config 5
CAFFE label file : 0x63a5e0
opencv_set_config 6
WARNING: Logging before InitGoogleLogging() is written to STDERR
E0205 17:50:15.609386 1962 common.cpp:114] Cannot create Cublas handle. Cublas won’t be available.
I0205 17:50:15.698453 1962 net.cpp:51] Initializing net from parameters:
name: “CaffeNet”
state {
phase: TEST
level: 0
}
layer {
name: “data”
type: “Input”
top: “data”
input_param {
shape {
dim: 10
dim: 3
dim: 227
dim: 227
}
}
}

layer {
name: “prob”
type: “Softmax”
bottom: “fc8”
top: “prob”
}
I0205 17:50:15.699630 1962 layer_factory.hpp:77] Creating layer data
I0205 17:50:15.699728 1962 net.cpp:84] Creating Layer data
I0205 17:50:15.699775 1962 net.cpp:380] data → data
I0205 17:50:15.801203 1962 net.cpp:122] Setting up data
I0205 17:50:15.801347 1962 net.cpp:129] Top shape: 10 3 227 227 (1545870)
I0205 17:50:15.801512 1962 net.cpp:137] Memory required for data: 6183480
I0205 17:50:15.801618 1962 layer_factory.hpp:77] Creating layer conv1
I0205 17:50:15.801797 1962 net.cpp:84] Creating Layer conv1
I0205 17:50:15.801882 1962 net.cpp:406] conv1 ← data
I0205 17:50:15.801997 1962 net.cpp:380] conv1 → conv1
OFParserGetVirtualDevice: virtual device driver node not found in proc device-tree
OFParserGetVirtualDevice: virtual device driver node not found in proc device-tree
LoadOverridesFile: looking for override file [/Calib/camera_override.isp] 1/16LoadOverridesFile: looking for override file [/data/nvcam/settings/camera_overrides.isp] 2/16LoadOverridesFile: looking for override file [/opt/nvidia/nvcam/settings/camera_overrides.isp] 3/16LoadOverridesFile: looking for override file [/var/nvidia/nvcam/settings/camera_overrides.isp] 4/16LoadOverridesFile: looking for override file [/data/nvcam/camera_overrides.isp] 5/16LoadOverridesFile: looking for override file [/data/nvcam/settings/e3326_front_P5V27C.isp] 6/16LoadOverridesFile: looking for override file [/opt/nvidia/nvcam/settings/e3326_front_P5V27C.isp] 7/16LoadOverridesFile: looking for override file [/var/nvidia/nvcam/settings/e3326_front_P5V27C.isp] 8/16---- imager: No override file found. ----
PRODUCER: Creating output stream
PRODUCER: Launching consumer thread
Failed to query video capabilities: Inappropriate ioctl for device
libv4l2_nvvidconv (0):(792) (INFO) : Allocating (10) OUTPUT PLANE BUFFERS Layout=1
libv4l2_nvvidconv (0):(808) (INFO) : Allocating (10) CAPTURE PLANE BUFFERS Layout=0
create vidoe converter return true
CONSUMER: Waiting until producer is connected…
PRODUCER: Starting repeat capture requests.
CONSUMER: Producer has connected; continuing.
F0205 17:50:16.197484 1962 cudnn_conv_layer.cpp:53] Check failed: status == CUDNN_STATUS_SUCCESS (4 vs. 0) CUDNN_STATUS_INTERNAL_ERROR
*** Check failure stack trace: ***
Aborted (core dumped)

please do help me run this sample and thanks in advance for all the suggestions to debug this

Hi,
We suggest run TensorRT and please refer to

tegra_multimedia_api\samples

tegra_multimedia_api\samples\04_video_dec_trt
tegra_multimedia_api\samples\backend
tegra_multimedia_api\samples\frontend

4_video_dec_trt
tegra_multimedia_api\samples\backend
tegra_multimedia_api\samples\frontend