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

nnp_fully_connected_output will get wrong result if batch-size != 2^n #43

Closed

tornadomeet opened this issue Dec 27, 2016 · 1 comment

tornadomeet commented Dec 27, 2016

hello, @Maratyszcza

i have add NNPACK to MXNet, apache/mxnet#4373 which support batch-size >= 1 on conv, max-pooling, fully-connected. but i found nnp_fully_connected_output will get wrong result if batch-size != 2^n, so i add some commit in https://github.com/tornadomeet/mxnet/blob/b7caa3bed94a08f2a285981b5051ba009422461a/src/operator/nnpack/nnpack_fully_connected-inl.h#L63-L65 .

does this is a konw bug? thanks.

BTW, i used a face detecton model called mtcnn for test, and found this problem.

Owner

Maratyszcza commented Dec 27, 2016

@tornadomeet Thank you for reporting. I didn't know about this problem, and it looks very strange, but I will check it.

tornadomeet mentioned this issue

There are some wrongs with nnp_fully_connected_output #44

Closed

Maratyszcza mentioned this issue

fma relu combination for convolution-output #31

Closed

Maratyszcza closed this as completed in

d64ddf0

tornadomeet mentioned this issue

update fc with nnpck apache/mxnet#5570

Merged

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