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

Fix DeprecationWarning: invalid escape sequence '\ ' in docstrings #3282

Merged
merged 1 commit into from
Feb 17, 2025
Merged

Fix DeprecationWarning: invalid escape sequence '\ ' in docstrings #3282

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
2 changes: 1 addition & 1 deletion nncf/experimental/torch/fx/transformations.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -688,7 +688,7 @@ def fq_weights_transformation(model: torch.fx.GraphModule) -> None:


def compress_post_quantize_transformation(model: torch.fx.GraphModule) -> None:
"""
r"""
Applies transformation to compress the weights to Int8 after the quantization step.
Starts by removing the Quantize/De-Quantize nodes for weight nodes by matching the pattern
to be like follows:
Expand Down
8 changes: 4 additions & 4 deletions nncf/openvino/graph/model_builder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,14 +59,14 @@ def _collect_graph_nodes(
output_ids: List[Tuple[str, int]],
node_mapping: Dict[str, ov.Node],
) -> List[ov.Node]:
"""
r"""
A method for aggregating layers to be further cloned.
Aggregation is designed in such a way that layers are listed from right to left,
as they pass from bottom to top. This is done in order to find all constants in the model and
to start graph creation from them (as well as Parameter layers), because
OpenVINO graph is created from top-down and cannot be created otherwise.

Legend: w - weigths, c - convert, il/ih - input low/high, ol/oh - output low/high
Legend: w - weights, c - convert, il/ih - input low/high, ol/oh - output low/high
(w)
|
(c) (il) (ih) (ol) (oh)
Expand Down Expand Up @@ -115,11 +115,11 @@ def build(
output_ids: List[Tuple[str, int]],
node_mapping: Dict[str, ov.Node],
) -> ov.Model:
"""
r"""
The basic method of the algorithm. This method uses an aggregated list of layers to be recreated.
Let us take a graph of this kind as an example:

Legend: w - weigths, c - convert, il/ih - input low/high, ol/oh - output low/high
Legend: w - weights, c - convert, il/ih - input low/high, ol/oh - output low/high
(w)
|
(c) (il) (ih) (ol) (oh)
Expand Down
Loading