Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) T4, RTX4000 • DeepStream Version DS 6.2 • JetPack Version (valid for Jetson only) • TensorRT Version 8.2.x • NVIDIA GPU Driver Version (valid for GPU only) 525.85.12 • Issue Type( questions, new requirements, bugs) Question • How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing) • Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
Hello,
I am working on face detection application and I would like to use nvdspreprocess for face alignment post face detection?
Will it possible to use nvdspreprocess with nvinferserver (Triton + grpc) deployment?
Do we get access to all output from face detector into nvdsprecess custom lib?
what do you mean about “face alignment post face detection”? nvdspreprocess is used to do preprocess.
Ans: Getting face co-ordinates from face detector, I want to crop face from input image and do some alignment, so can I use nvdspreprocess to do such operation.
Does nvdspreprocess element other inputs along with primary input?
streammux->pgie->nvdspreprocess->sgie->osd
pgie provides face co-ordinates and key points for face.
There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks
you mean accept? yes, from ds6.2, nvdspreprocess can work after pgie, the pipeline looks like pgie+ nvdspreprocess + sgie, please refer to sample \opt\nvidia\deepstream\deepstream\samples\configs\deepstream-app\source4_1080p_dec_preprocess_infer-resnet_preprocess_sgie_tiled_display_int8.txt