Replies: 9 comments
-
@sty1992928 , as far as I know, are you using this project ? |
Beta Was this translation helpful? Give feedback.
-
Onnxruntime has some unsolved perf problems with conv1d: microsoft/onnxruntime#7212 microsoft/onnxruntime#8513 We found only version 1.8.0 is somewhat performant (usually these issues are about bad configuration of cudnn / cudnn benchmarking workspace size). Please also report to onnxruntime to bump these issues in priority |
Beta Was this translation helpful? Give feedback.
-
I use cpu only,is this as expected? |
Beta Was this translation helpful? Give feedback.
-
I use cpu only, does cpu mode has the same perf problems? |
Beta Was this translation helpful? Give feedback.
-
Those issues are unrelated to CPU, so likely not... |
Beta Was this translation helpful? Give feedback.
-
Thank you anyway!The Int8 quant works,so my problem is temporarily gone. |
Beta Was this translation helpful? Give feedback.
-
hi,May I ask how you exported onnx? |
Beta Was this translation helpful? Give feedback.
-
Hi you can use torch.onnx.export to do the onnx export of torch module; |
Beta Was this translation helpful? Give feedback.
-
dear @xIaott-s, can you please share your code on how you have converted your model to onnx and quantized it? |
Beta Was this translation helpful? Give feedback.
-
Hi, I export the ecapa-tdnn model to onnx and use onnxruntime to inference. But the inference speed is slower than pytorch. Does anybody konw why?
Beta Was this translation helpful? Give feedback.
All reactions