Error in applying .uff model in the driveworks sample


When I trying to apply the uff model in the sample code of the driveworks, it gives me this error.
Could you help me with this problem?

./sample_object_detector --tensorRT_model=~/Desktop/testmodel.uff
Program Arguments:

nvrm_gpu: Bug 200215060 workaround enabled.
Initialize DriveWorks SDK v0.6.67
Release build with GNU 4.9.2 from v0.6.0-rc7-0-g51bd3aa against Vibrante PDK v5.0.5.0
TimeSource: monotonic epoch time offset is 1526408382694795
TimeSource: PTP ioctl returned error. Synchronized time will not be available.
TimeSource: Could not detect valid PTP time source at 'eth0'. Fallback to CLOCK_MONOTONIC.
SDK: Resources mounted from /usr/local/driveworks-0.6/data/resources
SDK: Create NvMediaDevice
SDK: use EGL display as provided
SDK: number of GPU devices detected 2
SDK: currently selected GPU device discrete ID 0
SAL: identified board as DrivePX2-TegraA
SensorFactory::createSensor() -> camera.virtual, video=.././data/samples/sfm/triangulation/video_0.h264,yuv2rgb=cuda
CameraNvMedia: no seek table found at .././data/samples/sfm/triangulation/, seeking is not available.
Camera image with 1280x800 at 30 FPS
nvmEglStProducerCreateCommon: Entered
nvmEglStProducerCreateCommon: Entered
Initializing TensorRT Network: ~/Desktop/testmodel.uff
Driveworks exception thrown: DW_FILE_NOT_FOUND: TensorRT file could not be found.

Dear zhisheng,
Driveworks 0.6 supports tensorrt model based on caffemodels. We will support uff models in next release.


In Driveworks 0.6, if I use Tensorflow, how could I apply trained model in Driveworks samples?


Dear zhisheng,
Driveworks 0.6 supports only caffe models.