HanG-CS
Results
2
comments of
HanG-CS
> In short, sparse convolution may not necessarily be faster than dense convolution in scoring scenarios.简而言之，在评分场景中，稀疏卷积不一定比密集卷积更快。 why?
> Do you only see NaNs in TRT? If it's a limitation of the model itself, you can debug with another backend, like ONNX-RT.您是否只在 TRT 中看到 NaN？如果这是模型本身的限制，您可以使用其他后端进行调试，例如 ONNX-RT。 Why --trt...