Need help to get driveworks sample running. Any idea what can be the problem?
./src/drivenet/drivenet/sample_drivenet
[20-11-2018 16:32:30] Initialize DriveWorks SDK v1.2.400
[20-11-2018 16:32:30] Release build with GNU 4.8.5 from v1.2.0-rc11-0-ga7f5475
[20-11-2018 16:32:30] Platform: Detected Generic x86 Platform
[20-11-2018 16:32:30] TimeSource: monotonic epoch time offset is 1542723880220026
[20-11-2018 16:32:30] Platform: number of GPU devices detected 1
[20-11-2018 16:32:30] Platform: currently selected GPU device discrete ID 0
[20-11-2018 16:32:30] SDK: Resources mounted from /usr/local/driveworks-1.2/samples/../data/resources
[20-11-2018 16:32:30] SensorFactory::createSensor() -> camera.virtual, dla=0,dlaEngineNo=0,enableFoveal=0,precision=fp32,stopFrame=0,video=/usr/local/driveworks-1.2/samples/../data/samples/raw/rccb.raw
[20-11-2018 16:32:30] CameraVirtual: The recorded RAW video appears to be a version 2, which is no longer supported
[20-11-2018 16:32:30] CameraRAW: no seek table found at /usr/local/driveworks-1.2/samples/../data/samples/raw/rccb.raw.seek, seeking is not available.
Camera image: 1920x1208
Camera image with 1920x1208 at 30 FPS
[20-11-2018 16:32:31] DriveNet: Running in FP32 mode.
[20-11-2018 16:32:31] Added linear block of size 22118400
[20-11-2018 16:32:31] Added linear block of size 7372800
[20-11-2018 16:32:31] Added linear block of size 3225600
[20-11-2018 16:32:31] DataConditioner: Scale transformation has been configured with 0.003922.
[20-11-2018 16:32:31] DataConditioner: Split transformation has been enabled.
[20-11-2018 16:32:31] DataConditioner: Value subtract transformation has been configured with {0.00000, 0.00000, 0.00000}.
[20-11-2018 16:32:31] CUDA cask failure at execution for trt_maxwell_scudnn_128x64_relu_medium_nn_v1.
[20-11-2018 16:32:31] caskConvolutionLayer.cpp (195) - Cuda Error in execute: 48
[20-11-2018 16:32:31] caskConvolutionLayer.cpp (195) - Cuda Error in execute: 48
[20-11-2018 16:32:31] CUDA cask failure at execution for trt_maxwell_scudnn_128x64_relu_medium_nn_v1.
[20-11-2018 16:32:31] caskConvolutionLayer.cpp (195) - Cuda Error in execute: 48
[20-11-2018 16:32:31] caskConvolutionLayer.cpp (195) - Cuda Error in execute: 48
nvidia-smi
Tue Nov 20 16:34:32 2018
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 396.37 Driver Version: 396.37 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 Quadro K2200 Off | 00000000:02:00.0 On | N/A |
| 42% 36C P8 1W / 39W | 201MiB / 4042MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 1819 G /usr/lib/xorg/Xorg 152MiB |
| 0 4849 G compiz 41MiB |
| 0 5867 G /usr/lib/firefox/firefox 1MiB |
| 0 6059 G /usr/lib/firefox/firefox 1MiB |
+-----------------------------------------------------------------------------+
nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2018 NVIDIA Corporation
Built on Tue_Jun_12_23:07:04_CDT_2018
Cuda compilation tools, release 9.2, V9.2.148
./mnistCUDNN
cudnnGetVersion() : 7102 , CUDNN_VERSION from cudnn.h : 7301 (7.3.1)
Host compiler version : GCC 5.4.0
There are 1 CUDA capable devices on your machine :
device 0 : sms 5 Capabilities 5.0, SmClock 1124.0 Mhz, MemSize (Mb) 4042, MemClock 2505.0 Mhz, Ecc=0, boardGroupID=0
Using device 0
Testing single precision
Loading image data/one_28x28.pgm
Performing forward propagation ...
Testing cudnnGetConvolutionForwardAlgorithm ...
Fastest algorithm is Algo 1
Testing cudnnFindConvolutionForwardAlgorithm ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: 0.022880 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: 0.035488 time requiring 3464 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: 0.044288 time requiring 57600 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: 0.266592 time requiring 2057744 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: 0.421344 time requiring 203008 memory
Resulting weights from Softmax:
0.0000000 0.9999399 0.0000000 0.0000000 0.0000561 0.0000000 0.0000012 0.0000017 0.0000010 0.0000000
Loading image data/three_28x28.pgm
Performing forward propagation ...
Resulting weights from Softmax:
0.0000000 0.0000000 0.0000000 0.9999288 0.0000000 0.0000711 0.0000000 0.0000000 0.0000000 0.0000000
Loading image data/five_28x28.pgm
Performing forward propagation ...
Resulting weights from Softmax:
0.0000000 0.0000008 0.0000000 0.0000002 0.0000000 0.9999820 0.0000154 0.0000000 0.0000012 0.0000006
Result of classification: 1 3 5
Test passed!
Testing half precision (math in single precision)
Loading image data/one_28x28.pgm
Performing forward propagation ...
Testing cudnnGetConvolutionForwardAlgorithm ...
Fastest algorithm is Algo 1
Testing cudnnFindConvolutionForwardAlgorithm ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: 0.023424 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: 0.031360 time requiring 3464 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: 0.040128 time requiring 28800 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: 0.263808 time requiring 2057744 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: 0.422848 time requiring 203008 memory
Resulting weights from Softmax:
0.0000001 1.0000000 0.0000001 0.0000000 0.0000563 0.0000001 0.0000012 0.0000017 0.0000010 0.0000001
Loading image data/three_28x28.pgm
Performing forward propagation ...
Resulting weights from Softmax:
0.0000000 0.0000000 0.0000000 1.0000000 0.0000000 0.0000714 0.0000000 0.0000000 0.0000000 0.0000000
Loading image data/five_28x28.pgm
Performing forward propagation ...
Resulting weights from Softmax:
0.0000000 0.0000008 0.0000000 0.0000002 0.0000000 1.0000000 0.0000154 0.0000000 0.0000012 0.0000006
Result of classification: 1 3 5
Test passed!