Skip to content

Revamp docs for Quantized ShuffleNetV2 #6028

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 1 commit into from
May 16, 2022
Merged

Revamp docs for Quantized ShuffleNetV2 #6028

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
27 changes: 27 additions & 0 deletions docs/source/models/shufflenetv2_quant.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
Quantized ShuffleNet V2
=======================

.. currentmodule:: torchvision.models.quantization

The Quantized ShuffleNet V2 model is based on the `ShuffleNet V2: Practical Guidelines for Efficient
CNN Architecture Design <https://arxiv.org/abs/1807.11164>`__ paper.


Model builders
--------------

The following model builders can be used to instantiate a quantized ShuffleNetV2
model, with or without pre-trained weights. All the model builders internally rely
on the ``torchvision.models.quantization.shufflenetv2.QuantizableShuffleNetV2``
base class. Please refer to the `source code
<https://github.com/pytorch/vision/blob/main/torchvision/models/quantization/shufflenetv2.py>`_
for more details about this class.

.. autosummary::
:toctree: generated/
:template: function.rst

shufflenet_v2_x0_5
shufflenet_v2_x1_0
shufflenet_v2_x1_5
shufflenet_v2_x2_0
1 change: 1 addition & 0 deletions docs/source/models_new.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,6 +206,7 @@ pre-trained weights:
models/mobilenetv2_quant
models/mobilenetv3_quant
models/resnet_quant
models/shufflenetv2_quant

|

Expand Down
119 changes: 93 additions & 26 deletions torchvision/models/quantization/shufflenetv2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,8 +66,11 @@ def fuse_model(self, is_qat: Optional[bool] = None) -> None:
r"""Fuse conv/bn/relu modules in shufflenetv2 model

Fuse conv+bn+relu/ conv+relu/conv+bn modules to prepare for quantization.
Model is modified in place. Note that this operation does not change numerics
and the model after modification is in floating point
Model is modified in place.

.. note::
Note that this operation does not change numerics
and the model after modification is in floating point
"""
for name, m in self._modules.items():
if name in ["conv1", "conv5"] and m is not None:
Expand Down Expand Up @@ -205,19 +208,35 @@ def shufflenet_v2_x0_5(
) -> QuantizableShuffleNetV2:
"""
Constructs a ShuffleNetV2 with 0.5x output channels, as described in
`"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design"
<https://arxiv.org/abs/1807.11164>`_.
`ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
<https://arxiv.org/abs/1807.11164>`__.

.. note::
Note that ``quantize = True`` returns a quantized model with 8 bit
weights. Quantized models only support inference and run on CPUs.
GPU inference is not yet supported.

Args:
weights (ShuffleNet_V2_X0_5_QuantizedWeights or ShuffleNet_V2_X0_5_Weights, optional): The pretrained
weights for the model
progress (bool): If True, displays a progress bar of the download to stderr
quantize (bool): If True, return a quantized version of the model
weights (:class:`~torchvision.models.quantization.ShuffleNet_V2_X0_5_QuantizedWeights` or :class:`~torchvision.models.ShuffleNet_V2_X0_5_Weights`, optional): The
pretrained weights for the model. See
:class:`~torchvision.models.quantization.ShuffleNet_V2_X0_5_QuantizedWeights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the download to stderr.
Default is True.
quantize (bool, optional): If True, return a quantized version of the model.
Default is False.
**kwargs: parameters passed to the ``torchvision.models.quantization.ShuffleNet_V2_X0_5_QuantizedWeights``
base class. Please refer to the `source code
<https://github.com/pytorch/vision/blob/main/torchvision/models/quantization/shufflenetv2.py>`_
for more details about this class.

.. autoclass:: torchvision.models.quantization.ShuffleNet_V2_X0_5_QuantizedWeights
:members:

.. autoclass:: torchvision.models.ShuffleNet_V2_X0_5_Weights
:members:
:noindex:
"""
weights = (ShuffleNet_V2_X0_5_QuantizedWeights if quantize else ShuffleNet_V2_X0_5_Weights).verify(weights)
return _shufflenetv2(
Expand All @@ -242,19 +261,35 @@ def shufflenet_v2_x1_0(
) -> QuantizableShuffleNetV2:
"""
Constructs a ShuffleNetV2 with 1.0x output channels, as described in
`"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design"
<https://arxiv.org/abs/1807.11164>`_.
`ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
<https://arxiv.org/abs/1807.11164>`__.

.. note::
Note that ``quantize = True`` returns a quantized model with 8 bit
weights. Quantized models only support inference and run on CPUs.
GPU inference is not yet supported.

Args:
weights (ShuffleNet_V2_X1_0_QuantizedWeights or ShuffleNet_V2_X1_0_Weights, optional): The pretrained
weights for the model
progress (bool): If True, displays a progress bar of the download to stderr
quantize (bool): If True, return a quantized version of the model
weights (:class:`~torchvision.models.quantization.ShuffleNet_V2_X1_0_QuantizedWeights` or :class:`~torchvision.models.ShuffleNet_V2_X1_0_Weights`, optional): The
pretrained weights for the model. See
:class:`~torchvision.models.quantization.ShuffleNet_V2_X1_0_QuantizedWeights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the download to stderr.
Default is True.
quantize (bool, optional): If True, return a quantized version of the model.
Default is False.
**kwargs: parameters passed to the ``torchvision.models.quantization.ShuffleNet_V2_X1_0_QuantizedWeights``
base class. Please refer to the `source code
<https://github.com/pytorch/vision/blob/main/torchvision/models/quantization/shufflenetv2.py>`_
for more details about this class.

.. autoclass:: torchvision.models.quantization.ShuffleNet_V2_X1_0_QuantizedWeights
:members:

.. autoclass:: torchvision.models.ShuffleNet_V2_X1_0_Weights
:members:
:noindex:
"""
weights = (ShuffleNet_V2_X1_0_QuantizedWeights if quantize else ShuffleNet_V2_X1_0_Weights).verify(weights)
return _shufflenetv2(
Expand All @@ -271,19 +306,35 @@ def shufflenet_v2_x1_5(
) -> QuantizableShuffleNetV2:
"""
Constructs a ShuffleNetV2 with 1.5x output channels, as described in
`"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design"
<https://arxiv.org/abs/1807.11164>`_.
`ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
<https://arxiv.org/abs/1807.11164>`__.

.. note::
Note that ``quantize = True`` returns a quantized model with 8 bit
weights. Quantized models only support inference and run on CPUs.
GPU inference is not yet supported.

Args:
weights (ShuffleNet_V2_X1_5_QuantizedWeights or ShuffleNet_V2_X1_5_Weights, optional): The pretrained
weights for the model
progress (bool): If True, displays a progress bar of the download to stderr
quantize (bool): If True, return a quantized version of the model
weights (:class:`~torchvision.models.quantization.ShuffleNet_V2_X1_5_QuantizedWeights` or :class:`~torchvision.models.ShuffleNet_V2_X1_5_Weights`, optional): The
pretrained weights for the model. See
:class:`~torchvision.models.quantization.ShuffleNet_V2_X1_5_QuantizedWeights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the download to stderr.
Default is True.
quantize (bool, optional): If True, return a quantized version of the model.
Default is False.
**kwargs: parameters passed to the ``torchvision.models.quantization.ShuffleNet_V2_X1_5_QuantizedWeights``
base class. Please refer to the `source code
<https://github.com/pytorch/vision/blob/main/torchvision/models/quantization/shufflenetv2.py>`_
for more details about this class.

.. autoclass:: torchvision.models.quantization.ShuffleNet_V2_X1_5_QuantizedWeights
:members:

.. autoclass:: torchvision.models.ShuffleNet_V2_X1_5_Weights
:members:
:noindex:
"""
weights = (ShuffleNet_V2_X1_5_QuantizedWeights if quantize else ShuffleNet_V2_X1_5_Weights).verify(weights)
return _shufflenetv2(
Expand All @@ -300,19 +351,35 @@ def shufflenet_v2_x2_0(
) -> QuantizableShuffleNetV2:
"""
Constructs a ShuffleNetV2 with 2.0x output channels, as described in
`"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design"
<https://arxiv.org/abs/1807.11164>`_.
`ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
<https://arxiv.org/abs/1807.11164>`__.

.. note::
Note that ``quantize = True`` returns a quantized model with 8 bit
weights. Quantized models only support inference and run on CPUs.
GPU inference is not yet supported.

Args:
weights (ShuffleNet_V2_X2_0_QuantizedWeights or ShuffleNet_V2_X2_0_Weights, optional): The pretrained
weights for the model
progress (bool): If True, displays a progress bar of the download to stderr
quantize (bool): If True, return a quantized version of the model
weights (:class:`~torchvision.models.quantization.ShuffleNet_V2_X2_0_QuantizedWeights` or :class:`~torchvision.models.ShuffleNet_V2_X2_0_Weights`, optional): The
pretrained weights for the model. See
:class:`~torchvision.models.quantization.ShuffleNet_V2_X2_0_QuantizedWeights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the download to stderr.
Default is True.
quantize (bool, optional): If True, return a quantized version of the model.
Default is False.
**kwargs: parameters passed to the ``torchvision.models.quantization.ShuffleNet_V2_X2_0_QuantizedWeights``
base class. Please refer to the `source code
<https://github.com/pytorch/vision/blob/main/torchvision/models/quantization/shufflenetv2.py>`_
for more details about this class.

.. autoclass:: torchvision.models.quantization.ShuffleNet_V2_X2_0_QuantizedWeights
:members:

.. autoclass:: torchvision.models.ShuffleNet_V2_X2_0_Weights
:members:
:noindex:
"""
weights = (ShuffleNet_V2_X2_0_QuantizedWeights if quantize else ShuffleNet_V2_X2_0_Weights).verify(weights)
return _shufflenetv2(
Expand Down