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

feat(//tests): Update rtol and atol based tolerance for test cases #1055

Merged
merged 3 commits into from
Jun 22, 2022
Merged

feat(//tests): Update rtol and atol based tolerance for test cases #1055

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c7f0147
feat(//tests): Update rtol and atol based tolerance for test
andi4191 May 11, 2022
00adb21
chore!: Changing the names of tensor
andi4191 May 31, 2022
0f26bed
chore: Applying lint
andi4191 Jun 2, 2022
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
5 changes: 3 additions & 2 deletions tests/util/util.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,13 +5,14 @@ namespace torch_tensorrt {
namespace tests {
namespace util {

bool almostEqual(const at::Tensor& a, const at::Tensor& b, float threshold, float atol = 1e-8, float rtol = 1e-5) {
bool almostEqual(const at::Tensor& a, const at::Tensor& b, float atol = 1e-8, float rtol = 1e-5) {
LOG_GRAPH(a << std::endl << b << std::endl);
auto a_float = a.toType(at::kFloat);
auto b_float = b.toType(at::kFloat);

auto diff = a_float - b_float;
auto result = diff.abs().max().item<float>() - (atol + rtol * b.abs().max().item<float>());
auto result = diff.abs().max().item<float>();
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This equation is still confusing (see #1052)

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Based on the discussion in 1052, is this resolved? Anurag mentioned we need this PR for DLFW release.

auto threshold = atol + (rtol * b.abs().max().item<float>());

std::cout << "Max Difference: " << result << std::endl;
std::cout << "Acceptable Threshold: " << threshold << std::endl;
Expand Down
2 changes: 1 addition & 1 deletion tests/util/util.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ namespace torch_tensorrt {
namespace tests {
namespace util {

bool almostEqual(const at::Tensor& a, const at::Tensor& b, float threshold, float atol = 1e-8, float rtol = 1e-5);
bool almostEqual(const at::Tensor& a, const at::Tensor& b, float atol = 1e-8, float rtol = 1e-5);

bool exactlyEqual(const at::Tensor& a, const at::Tensor& b);

Expand Down