Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) Jetson
• DeepStream Version 5.0
• JetPack Version (valid for Jetson only) 4.4
• TensorRT Version 7.1
• NVIDIA GPU Driver Version (valid for GPU only)
I trained a yolov3 model with my dataset in nvidia transfer learning toolkit, exported and tlt-converted to trt.engine file with int8 calibration file for Jetson Xavier.
The model working well in TLT jupyter notbook environment, it can detect objects, but when I use deepstream-test3-app to depoly this model, nothing detected, the obj_metadata from pgie is empty.
What I’ve done
- Train a yolov3 via TLT.
- Export and convert to trt.engine with int8 calibration file.
- Build the TRT-OSS for Jetson, I just copied the .so file provided in the deepstream-tlt-app repo, it says the trt 7.1 version is a little different from ver 7.0, but I did’t build it from scratch since you’ve provide it.
- Build the deepstream-custom-app, copy the
libnvds_infercustomparser_yolov3_tlt.soto my app folder (duplicated from deepstream-test3).
- Configure the pgie_config.txt, to parse my custom yolov3 trt.engine and other terms.
- Build my app and running.
- Nothing detected in the osd result. My program running smoothly, the log says it’s already loaded my model, just nothing detected.
What I’ve tried
- Decrease the confidence threshold to 0.01, nothing happened.
- Check the
obj_metagenerated after pgie, it’s completely empty, no objects would be counted.
- Double check the model, it can detect objects from images in TLT environment.
- Something similar with my problem: Custom YOLOv3 model in DeepStream 5.0