Skip to content

[Big Tensor]Fix accuracy diff for paddle.nn.functional.adaptive_max_pool3d API. #74279

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

Merged
merged 1 commit into from
Jul 31, 2025
Merged

[Big Tensor]Fix accuracy diff for paddle.nn.functional.adaptive_max_pool3d API. #74279

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 4 additions & 7 deletions paddle/phi/kernels/funcs/pooling.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,18 +126,15 @@ class LPPoolGrad {

/* used for adaptive pool to calculate start and end index of each divided grid
*/
template <typename T = int>
template <typename T = int64_t>
HOSTDEVICE inline T AdaptStartIndex(T ph, T input_size, T output_size) {
return static_cast<T>(
floor(static_cast<float>(ph * input_size) / output_size));
return (ph * input_size) / output_size;
}

template <typename T = int>
template <typename T = int64_t>
HOSTDEVICE inline T AdaptEndIndex(T ph, T input_size, T output_size) {
return static_cast<T>(
ceil(static_cast<float>((ph + 1) * input_size) / output_size));
return ((ph + 1) * input_size + output_size - 1) / output_size;
}

/* used for fractional pool to calculate start and end index of each divided
* grid
*/
Expand Down