We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
测试函数为: test/test_onnx.py/test_linear()
onnx结果:
带bias的linear层转换成Gemm+Add,不带bias的linear层转换成Gemm。其中Gemm的bias都是为1维。
是否应该改为: 带bias的linear层转换成Gemm,其中gemm的bias为oc维; 不带bias的linear层转换成Gemm, bias为空?
The text was updated successfully, but these errors were encountered:
目前,目前我们的mgeconvert是基于dump出的细粒度cpp图的,由于python层linear的实现是matmul + add,导致dump出的mge的op也是matmul + add,从而导致转到onnx也是matmul + add。 针对这个问题,我们在caffe转换器中加了pattern match以解决conv+bias, linear + bias的问题,见代码,后续我们重构一下,在解析mge层实现这种策略以支持onnx等其他框架。 另外,我们正在开发更高层表达的traced module以彻底解决这些问题
Sorry, something went wrong.
No branches or pull requests
测试函数为:
test/test_onnx.py/test_linear()
onnx结果:
带bias的linear层转换成Gemm+Add,不带bias的linear层转换成Gemm。其中Gemm的bias都是为1维。
是否应该改为:
带bias的linear层转换成Gemm,其中gemm的bias为oc维;
不带bias的linear层转换成Gemm, bias为空?
The text was updated successfully, but these errors were encountered: