-
Notifications
You must be signed in to change notification settings - Fork 4.2k
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
convolution_3x3.h 中 conv3x3s1_winograd64_neon5/conv3x3s1_winograd64_neon4 效果不对 #517
Comments
我发现另一个是pool层结果不对。 2.042570 2.042570 1.477021 0.012891 0.014708 0.000303 android结果: 0.152344 0.160156 0.542969 0.012891 0.014708 0.000303 从源代码中打印的结果来看,pc端跑的代码与android跑的代码是一样的。android中还用到了汇编代码。 |
我是逐层打印Mat结果,Conv层结果没有差别。 |
请提供下 conv pooling 的调用参数 kernel stride pad 等,以及输入blob的w h c |
bottom_blob: w: 74, h: 102, c: 40, n: 1; cstep: 7548 bottom_blob已经做了copy_make_border, pad_w == pad_h == 1 请帮忙分析一下,谢谢~ |
@spacegrass x86 和 armv7 aarch64 上测试没有问题,检查下你自己做的 padding 是不是有问题 |
问题解决了,没有创建winograd的kernel,谢谢 |
我试了一下PC/ANDROID两个版本的winograd,发现效果都不对;64位版本。这个有人发现类似问题么?
The text was updated successfully, but these errors were encountered: