Skip to content

[Accuracy diff No.70] Fix accuracy diff for topk API #217

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 5 commits into from
Jun 5, 2025
Merged

[Accuracy diff No.70] Fix accuracy diff for topk API #217

Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
3940ca9
fix
ooooo-create May 30, 2025
e5dd429
refine data_gen to avoid unstable behavier accuracy check
ooooo-create May 31, 2025
eadc457
apply review
ooooo-create Jun 2, 2025
5ade436
apply review
ooooo-create Jun 4, 2025
ca21f30
Merge branch 'main' of https://github.com/PFCCLab/PaddleAPITest into …
ooooo-create Jun 4, 2025
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
10 changes: 10 additions & 0 deletions tester/api_config/config_analyzer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1760,6 +1760,16 @@ def get_padding_offset(bsz, max_seq_len, seq_lens_this_time):
else:
# self.check_arg(api_config, 1, "other"):
self.numpy_tensor = self.get_random_numpy_tensor(self.shape, self.dtype, min=-10, max=10)
elif api_config.api_name in {"paddle.Tensor.topk", "paddle.topk"}:
x_numel = self.numel()
if self.dtype in {"float32", "float64"}:
unique_values = numpy.linspace(-1, 1, num=x_numel, dtype=self.dtype)
permuted_values = numpy.random.permutation(unique_values)
self.numpy_tensor = permuted_values.reshape(self.shape)
elif self.dtype in {"int32", "int64"}:
self.numpy_tensor = numpy.random.choice(numpy.arange(-x_numel, x_numel), size=self.shape, replace=False).astype(self.dtype)
else:
raise ValueError(f"Unsupported dtype {self.dtype} for paddle.topk")

if self.numpy_tensor is None:
if USE_CACHED_NUMPY:
Expand Down