tensorrt_demos

tensorrt_demos copied to clipboard

failed to build the TensorRT engine

3

Hi @jkjung-avt first, thank you for your amazing work, I have tested this demo on jetson tx2 and it’s work! and i wanted to test it on jetson xavier, i...

soukaina11111

The mtcnn consumes takes alot of RAM.

8

2.35GB ram is being consumed. Any way to reduce it? Any reason why it is this much?

aafaqin

WARNING:root:Camera: starting while cap is not opened!

1

Hi, Good evening i am facing following error while passing --rtsp stream: WARNING:root:Camera: starting while cap is not opened! ERROR: failed to open camera! I've tried all available solutions in...

starlord263

yolov7 support?

1

any plan to support this https://github.com/WongKinYiu/yolov7

akashAD98

Drop in mAP after TensorRT optimization

29

@jkjung-avt Hi, could we work together on the problem of the reduced accuracy? I believe I have similar issues in my implementation and I do not use any onnx conversion...

philipp-schmidt

Squared actual batch size when exporting yolov4-tiny, from yolo to onnx to trt

2

Hi, thanks for having this awesome repo, it helps a lot when dealing with tensorrt. I am trying to export a tensorrt model of yolov4-tiny (nc=1) with a batch size...

Pochingto

When I am running YOLOv4 on JETSON NANO with 288x192 input size the detection time are different for all detection mostly it gives 10FPS but sometimes detection time drops to...

aafaqin

mAP drops in the converted SSD mobilenet v2

2

I followed all the steps, you have mentioned for converting TensorFlow SSD model v2 1.14 into TensorRT bin. I updated the buildengine.py file and graphsurgeon converter for new Jetpack support....

dsnsabari

Xavier yolo to Int8 met error

2

Hi I've met the error below during converting from onnx model to int8 trt engine on Xavier I just followed the step in instructions and exec: python3 onnx_to_tensorrt.py -v --int8...

herschelpuu

Yolov4-tiny calibration error

1

I am getting the following error when calibrating a yolov4-tiny model. I can convert it successfully to tensorrt. Any ideas why? 

pteran2403