Peoplenet performance on Jetson - NVIDIA Developer Forums Hi All, I have implemented deepstream pipeline which uses peoplenet model for inference It gets the raw frame from appsrc and push it to deepstream pipeline for inference From the peoplenet ngc It says that It gives more than 200 fps inference speed for resnet34 model But I am getting max 80 fps I am providing 16 channels stream as input, and per channel I am only able to get max 5 fps
PeopleNet not Detecting Bags - NVIDIA Developer Forums Hi, I tested peoplenet on pruned_quantized_decrypted_v2 3 4 and deployable_quantized_onnx_v2 6 3 and realized that the model detects person and face well but detects no bag
Peoplenet - Page 1 | TruckingTruth Forum The company I'm gonna go to has peoplenet Can anyone enlighten me on the difference in this and Qualcomm Does peoplenet have a gps on it ? Please give me info - Page 1
How do I run PeopleNet + NvDeepSORT? - NVIDIA Developer Forums • Hardware Platform (Jetson GPU) NVIDIA RTX A3000 • DeepStream Version 6 2 • TensorRT Version • NVIDIA GPU Driver Version (valid for GPU only) I was reading this Gst-nvtracker — DeepStream 6 2 Release documentation I want to run PeopleNet + NvDeepSORT on my Ubuntu device How do I do it?
Error during trtexec PeopleNet ONNX Model Engine file generation Turns out I was using an incorrect version of models which was causing other problems too in another Pipeline Here is the solution - Unable to run PeopleNet - Engine file generation failure Model v2 3 3 is expected to work with DeepStream 7 0
How to train fine-tune PeopleNet on 10 classes? Yes, but it is suggested to use YOLO_v4_tiny network instead to finetune so many classes It will get much better result then detecnet_v2 network