squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

remove restriction of stride == kernel in nhwc_pooling (#1896)

Browse Source
This commit is contained in:
LiuQiang 2024-11-07 03:54:53 +08:00 committed by GitHub
parent 9004ed2d1b
commit 32e3c38aef
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tools/util/include/cutlass/util/device_nhwc_pooling.h
View File

@ -361,9 +361,6 @@ void pooling_nhwc(cutlass::Tensor4DCoord input_tensor_size,
assert(input_tensor_size.n() == output_tensor_size.n() && assert(input_tensor_size.n() == output_tensor_size.n() &&
input_tensor_size.c() == output_tensor_size.c()); input_tensor_size.c() == output_tensor_size.c());
assert(filter_tensor_size.h() == stride.row() &&
filter_tensor_size.w() == stride.column());
const int N = input_tensor_size.n(); const int N = input_tensor_size.n();
const int H = input_tensor_size.h(); const int H = input_tensor_size.h();
const int W = input_tensor_size.w(); const int W = input_tensor_size.w();