New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

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

Jump to bottom

缺少torch.einsum("ijm,imkl->ijkl", v_920, v_486)支持 #5766

Open

Baiyuetribe opened this issue Nov 6, 2024 · 0 comments

Contributor

Baiyuetribe commented Nov 6, 2024

问题

einsum中缺少这种情况的支持。

ncnn/tools/pnnx/tests/test_torch_einsum.py

Line 27 in c32442a

a2 = torch.einsum('ijk', z0)

这个einsum操作 ijm,imkl->ijkl 的含义是：

输入有两个张量：形状为(i,j,m)和(i,m,k,l)的张量
在m维度上进行求和收缩
输出形状为(i,j,k,l)的张量

补充

个人能力有限，希望大佬支持下

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment