jetson-inference issue

Autonomous Machines Jetson & Embedded Systems Jetson AGX Xavier
1

Hi
when i run this ./segnet-camera with my jetson xavier and my logitech c930e camera, i have this error:

[TRT] TensorRT version 5.0.3
[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, INT8
[TRT] selecting fastest native precision for GPU: FP16
[TRT] attempting to open engine cache file networks/FCN-Alexnet-Cityscapes-HD/snapshot_iter_367568.caffemodel.2.1.GPU.FP16.engine
[TRT] cache file not found, profiling network model on device GPU
[TRT] device GPU, loading networks/FCN-Alexnet-Cityscapes-HD/deploy.prototxt networks/FCN-Alexnet-Cityscapes-HD/snapshot_iter_367568.caffemodel
[TRT] CaffeParser: Could not parse binary model file
[TRT] CaffeParser: Could not parse model file
[TRT] device GPU, failed to parse caffe network
device GPU, failed to load networks/FCN-Alexnet-Cityscapes-HD/snapshot_iter_367568.caffemodel
segNet – failed to initialize.
segnet-camera: failed to initialize imageNet

Also, i try with this:
./segnet-camera --prototxt=$NET/deploy.prototxt --model=$NET/snapshot_iter_2756640.caffemodel --labels=$NET/cityscapes-labels.txt --colors=$NET/cityscapes-deploy-colors.txt

[TRT] TensorRT version 5.0.3
[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, INT8
[TRT] selecting fastest native precision for GPU: FP16
[TRT] attempting to open engine cache file .2.1.GPU.FP16.engine
[TRT] cache file not found, profiling network model on device GPU
[TRT] device GPU, loading
[TRT] CaffeParser: Could not open file
[TRT] CaffeParser: Could not parse model file
[TRT] device GPU, failed to parse caffe network
device GPU, failed to load
segNet – failed to initialize.
segnet-camera: failed to initialize imageNet

Any help please !!

2

Hi,

The error occurs when loading the setNet model:

device GPU, failed to load networks/FCN-Alexnet-Cityscapes-HD/snapshot_iter_367568.caffemodel

Could you check if the model do exist on the folder first?
${execution DIR}/networks/FCN-Alexnet-Cityscapes-HD/deploy.prototxt
${execution DIR}/networks/FCN-Alexnet-Cityscapes-HD/snapshot_iter_367568.caffemodel

Thanks.

3

Hello

Seeing same on fresh install on jetson nano -

michael@dizzyneuron:~/jetson-inference/build/aarch64/bin$ ./segnet-camera
[gstreamer] initialized gstreamer, version 1.14.4.0
[gstreamer] gstCamera attempting to initialize with GST_SOURCE_NVARGUS, camera 0
[gstreamer] gstCamera pipeline string:
nvarguscamerasrc sensor-id=0 ! 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, camera 0

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

segNet – loading segmentation network model from:
– prototxt: networks/FCN-Alexnet-Cityscapes-SD/deploy.prototxt
– model: networks/FCN-Alexnet-Cityscapes-SD/snapshot_iter_114860.caffemodel
– labels: networks/FCN-Alexnet-Cityscapes-SD/cityscapes-labels.txt
– colors: networks/FCN-Alexnet-Cityscapes-SD/cityscapes-deploy-colors.txt
– input_blob ‘data’
– output_blob ‘score_fr_21classes’
– batch_size 1

[TRT] TensorRT version 5.1.6
[TRT] loading NVIDIA plugins…
[TRT] Plugin Creator registration succeeded - GridAnchor_TRT
[TRT] Plugin Creator registration succeeded - NMS_TRT
[TRT] Plugin Creator registration succeeded - Reorg_TRT
[TRT] Plugin Creator registration succeeded - Region_TRT
[TRT] Plugin Creator registration succeeded - Clip_TRT
[TRT] Plugin Creator registration succeeded - LReLU_TRT
[TRT] Plugin Creator registration succeeded - PriorBox_TRT
[TRT] Plugin Creator registration succeeded - Normalize_TRT
[TRT] Plugin Creator registration succeeded - RPROI_TRT
[TRT] Plugin Creator registration succeeded - BatchedNMS_TRT
[TRT] completed loading NVIDIA plugins.
[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 .1.1.GPU.FP16.engine
[TRT] cache file not found, profiling network model on device GPU

error: model file ‘networks/FCN-Alexnet-Cityscapes-SD/snapshot_iter_114860.caffemodel’ was not found.
if loading a built-in model, maybe it wasn’t downloaded before.

    Run the Model Downloader tool again and select it for download:

       $ cd <jetson-inference>/tools
       $ ./download-models.sh

segNet – failed to initialize.
segnet-camera: failed to initialize imageNet

I believe problem is that the actual file is snapshot_iter_2756640.caffemodel. But am unable to find where to change.

Cheers, Michael

4

Hello Michael,

assuming you have solved the issue already…it seems to be hard coded in
…/jetson-inferences/c/segNet.cpp, line 119

I renamed the snapshot in …/bin/networks - segnet-camera starts

Cheers Mike