Need TensorRT Engine for PeopleNet (A100 + TRT 10.13)

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

Hi,

I need a pre-built TensorRT engine file for PeopleNet ResNet34 INT8. I have the .etlt model but can’t build the engine locally.

Request:

  • Convert resnet34_peoplenet_int8.etlt → .engine file
  • Target: A100 GPU, TensorRT 10.13, CUDA 12.2

Build command (if you have DeepStream/TAO):
tao-converter -k nvidia_tlt -d 3,544,960
-o output_cov/Sigmoid,output_bbox/BiasAdd
-e resnet34_peoplenet_int8.engine -t int8
-c resnet34_peoplenet_int8_calib.txt
models/resnet34_peoplenet_int8.etlt

Takes ~5 min with DeepStream. Can you help?

Thanks!

2

You can some versions of peoplenet in ngc. For example, https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/models/peoplenet/files?version=deployable_quantized_onnx_v2.6.3.
Then you can use trtexec to generate the engine. An example is in TRTEXEC with DetectNet-v2 — Tao Toolkit.

3

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.

4

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.