-
Notifications
You must be signed in to change notification settings - Fork 28
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.
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
fast Depthwise mxnet operator #8
Comments
@KeyKy Have some good idea or implement on CPU T-T ?? |
@ccJia fast depthwise operator (which num_group == num_outputs) should be calculated in multi-threaded channel-by-channel. According to tencent's ncnn, I think sliding window (highly optimized, which also using in BVLC/caffe#5665) maybe faster than im2col+GEMM. |
@KeyKy OK, thank you . Let me have a try ^-^. |
@ccJia looking forward to your job. Could you share with me after you have done the work? ^-^ |
@KeyKy Some of my friends told me that the direct convolution like NCNN is not work..... |
@ccJia Did they explain the reason or they try? |
@KeyKy They tried on Win. |
@ccJia OK. I will try it in my spare time. |
@KeyKy waiting your good news . |
@KeyKy thank you |
@KeyKy Would you mind update the fast depthwise operator. or could you describe the key for implement fast operator. Thank you.
The text was updated successfully, but these errors were encountered: