Sophia Chou

Hi, thanks for your quick reply! I modified the code and it worked! For people who wanna save quantized weights, basically the modification is that the LSQ module returns x...

Hi @zhutmost, The performance of quantized model is good! But I found that the inference time after quantization is slower, do you have any comments on this? Below is the...

Hi, thanks for your quick reply. Below is the code I modified from your repo. Due to the characteristics of my model, I didn't modify codes related to `QuanLinear`. When...

Honestly, it's still slow but I'm not dealing with this problem now. Thanks!

Hi, thanks for putting great efforts into this! And good luck with your paper~ I followed the instructions on [Readme - installation](https://github.com/kuielab/mdx-net-submission/tree/leaderboard_A#installation) for Linux environment, and it was fine. But...

Hello, I installed `onnxruntime`, same as `environment.yml`. ``` $ pip list | grep onnxruntime onnxruntime 1.7.0 ```

Thank you guys, it's working! :)