Yolov5s performances problem?

Question

Yolov5s performances problem?

Closed this issue 4 years ago · 7 comments

It seems like the performances on example video very bad, any idea on which issues?
The bounding boxes looks like not very stable.

Answer 1 · 2020-09-06T05:03:00.000Z

your code which seems like using the NvDsInferYoloCudaEngineGet for parsing the tensorrt engine, is this correct??

Answer 2 · 2020-09-08T07:59:00.000Z

I have no problem. I can run yolov5 in deep stream 5.0 with fp16 model in a Xavier about 60 fps. Of course, the detect class num also influence the performance.

Answer 3 · 2020-09-08T09:12:08.000Z

@DanaHan I'm Glad to hear that! Maybe my model have some problem I would like to try again with your steps. Just in case, how did you run the app? Is it using the deepstream-app -c config_file?

Answer 4 · 2020-09-08T09:18:31.000Z

LD_PRELOAD=$PWD/libmyplugin && deepstream-app -c config_file

Answer 5 · 2020-09-08T09:23:25.000Z

your code which seems like using the NvDsInferYoloCudaEngineGet for parsing the tensorrt engine, is this correct??

I am read all source codes recently. It seems that NvDsInferYoloCudaEngineGet is called only when you use non-tensorrt engine model (ONNX,UFFT, etc). And this function seems used to build engine model. I'm not sure whether this is correct.

Answer 6 · 2020-09-08T12:08:38.000Z

@DanaHan I tried again with your apps it seems like even "Person" class not predicted very well, your test seems like perform very well on Person? And I have tried to replace the .cu files from this issue #3. It classify my face as "cup" and my body as diningtable

Answer 7 · 2020-09-08T12:58:18.000Z

@DanaHan I delete all files and followed again your step, it works well!
Seems like the weight of the yolov5s.pt not really good, I redownload all the weights and tensorrtx, and your repository. it work fine !