Skip to content

[Quantization] Fix static quantize runner usage. #26624

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −1
Open

[Quantization] Fix static quantize runner usage. #26624

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 1 addition & 0 deletions onnxruntime/python/tools/quantization/registry.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,6 +87,7 @@
"LayerNormalization": QDQNormalization,
"BatchNormalization": QDQNormalization,
"TopK": QDQDirect8BitOp,
"CumSum": QDQDirect8BitOp,
}


Expand Down
2 changes: 1 addition & 1 deletion onnxruntime/python/tools/quantization/static_quantize_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ def __init__(self, model_path):
name2tensors = []
for data_dir in data_dirs:
name2tensor = {}
data_paths = [os.path.join(data_dir, a) for a in sorted(os.listdir(data_dir))]
data_paths = [os.path.join(data_dir, f"input_{input_idx}.pb") for input_idx in range(len(model_inputs))]
data_ndarrays = [self.read_onnx_pb_data(data_path) for data_path in data_paths]
for model_input, data_ndarray in zip(model_inputs, data_ndarrays, strict=False):
name2tensor[model_input.name] = data_ndarray
Expand Down