Hello, I have a question about nvidia tlt. I’m going to do AI processing for a still image. By the way, I am recommended dipstream sdk using gstreamer as an extension of tlt, but can I input the image and process it with this API? Or should we find another way?
Thank you
Yes, it is possible.
See Integrating TAO Models into DeepStream — TAO Toolkit 3.22.05 documentation
then
then
./deepstream-custom -c pgie_config_file -i <H264 or JPEG filename> [-b BATCH] [-d]
-h: print help info
-c: pgie config file, e.g. pgie_frcnn_tlt_config.txt
-i: H264 or JPEG input file
-b: batch size, this will override the value of "baitch-size" in pgie config file
-d: enable display, otherwise dump to output H264 or JPEG file
1 Like