Skip to content
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

[Fix] Fix roi_align npu bug #2862

Merged
merged 2 commits into from
Jul 10, 2023
Merged

[Fix] Fix roi_align npu bug #2862

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a91196f
fix roi align bug.
momo609 Jun 6, 2023
fb7032d
fix roi align bug.
momo609 Jul 4, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions mmcv/ops/csrc/pytorch/npu/roi_align_npu.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,13 +7,14 @@ void roi_align_forward_npu(Tensor input, Tensor rois, Tensor output,
Tensor argmax_y, Tensor argmax_x, int aligned_height,
int aligned_width, float spatial_scale,
int sampling_ratio, int pool_mode, bool aligned) {
int64_t roi_end_mode = 2;
if (!aligned) {
LOG(WARNING) << "The [aligned] attr in roi_align op is false";
roi_end_mode = 0;
}
int64_t aligned_height_64 = aligned_height;
int64_t aligned_width_64 = aligned_width;
int64_t sampling_ratio_64 = sampling_ratio;
int64_t roi_end_mode = 0;
OpCommand cmd;
cmd.Name("ROIAlign")
.Input(input)
Expand All @@ -35,7 +36,11 @@ void roi_align_backward_npu(Tensor grad_output, Tensor rois, Tensor argmax_y,
int64_t aligned_height_64 = aligned_height;
int64_t aligned_width_64 = aligned_width;
int64_t sampling_ratio_64 = sampling_ratio;
int64_t roi_end_mode = 0;
int64_t roi_end_mode = 2;
if (!aligned) {
LOG(WARNING) << "The [aligned] attr in roi_align_grad op is false";
roi_end_mode = 0;
}
c10::SmallVector<int64_t, SIZE> xdiff_shape =
at_npu::native::array_to_small_vector(grad_input.sizes());
OpCommand cmd;
Expand Down