deepstream-app version 5.0.0
CUDA Driver Version: 10.2
CUDA Runtime Version: 10.2
TensorRT Version: 7.0
cuDNN Version: 7.6
libNVWarp360 Version: 2.0.1d3
I pull the nvidia docker: nvcr.io/nvidia/deepstream:5.0.1-20.09-triton in nvidia V100
cd to /opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream-test1, then run
however, it print:
Now playing: /opt/nvidia/deepstream/deepstream-5.0/samples/streams/sample_720p.h264
then i wait one night…
V100 is compute card. you can change nveglglessink to fakesink in the sample.
- sink = gst_element_factory_make (“nveglglessink”, “nvvideo-renderer”);
+ sink = gst_element_factory_make (“fakesink”, “nvvideo-renderer”);
if you want to see the output, you can refer to function create_udpsink_bin in sources/apps/apps-common/src/deepstream_sink_bin.c to change the sink to rtspstreaming. you also can directly use deepstream-app which supports config file. you can set sink type directly in the config file.
i did this change
sink = gst_element_factory_make (“fakesink”, “nvvideo-renderer”); in deepstream_test1_app.c, then
make the project and run, but it still:
and i wait a long time…
the same sample can run in Jetson nano.
You still use the precompiled sample.
please run like ./deepstream-test1-app …/…/…/…/samples/streams/sample_720p.h264
Thank you so so so so much!! it wotks!
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.