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

fix doc style #61688

Merged
merged 1 commit into from
Feb 19, 2024
Merged

fix doc style #61688

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.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
10 changes: 6 additions & 4 deletions python/paddle/quantization/quantize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,8 +28,9 @@
class Quantization(metaclass=abc.ABCMeta):
r"""
Abstract class used to prepares a copy of the model for quantization calibration or quantization-aware training.

Args:
config(QuantConfig) - Quantization configuration
config(QuantConfig): Quantization configuration
"""

def __init__(self, config: QuantConfig):
Expand All @@ -43,10 +44,11 @@ def quantize(self, model: Layer, inplace=False):
def convert(self, model: Layer, inplace=False, remain_weight=False):
r"""Convert the quantization model to ONNX style. And the converted
model can be saved as inference model by calling paddle.jit.save.

Args:
model(Layer) - The quantized model to be converted.
inplace(bool, optional) - Whether to modify the model in-place, default is False.
remain_weight(bool, optional) - Whether to remain weights in floats, default is False.
model(Layer): The quantized model to be converted.
inplace(bool, optional): Whether to modify the model in-place, default is False.
remain_weight(bool, optional): Whether to remain weights in floats, default is False.

Return: The converted model

Expand Down