Improved yolov6 to have the same trt model inference speed under int8 and fp16 #5803
Unanswered
xiaoche-24
asked this question in
Q&A
Replies: 2 comments
-
Which runtime are you using? This issue should probably be moved there. |
Beta Was this translation helpful? Give feedback.
0 replies
-
I would move the issue to https://github.com/NVIDIA/TensorRT for more help. Thanks! |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Ask a Question
Question
I improved yolov6. After converting to tensorrt, the improved model's inference speed is faster than the original yolov6 under fp32 and fp16. However, after converting to int8, the speed of the original yolov6 has doubled (fp16:66fps -> int8:122fps ), and the speed of the improved yolov6 is (fp16: 100fps -> int8: 102fps). The speed is almost not improved. What is the reason? My improvement module includes split, concat, and DropPath operations. Onnx.opset is set to 12 because 13 will report an error.Because when using opset13 to convert tensorrt on NX, the following error will be reported:
Further information
Relevant Area:
Is this issue related to a specific model?
Model name:
Model opset: 12
Notes
Beta Was this translation helpful? Give feedback.
All reactions