File size: 8,973 Bytes
9c6594c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 |
from functools import partial
from typing import Any, Optional
from torch import nn
from ...transforms._presets import SemanticSegmentation
from .._api import register_model, Weights, WeightsEnum
from .._meta import _VOC_CATEGORIES
from .._utils import _ovewrite_value_param, handle_legacy_interface, IntermediateLayerGetter
from ..resnet import ResNet, resnet101, ResNet101_Weights, resnet50, ResNet50_Weights
from ._utils import _SimpleSegmentationModel
__all__ = ["FCN", "FCN_ResNet50_Weights", "FCN_ResNet101_Weights", "fcn_resnet50", "fcn_resnet101"]
class FCN(_SimpleSegmentationModel):
"""
Implements FCN model from
`"Fully Convolutional Networks for Semantic Segmentation"
<https://arxiv.org/abs/1411.4038>`_.
Args:
backbone (nn.Module): the network used to compute the features for the model.
The backbone should return an OrderedDict[Tensor], with the key being
"out" for the last feature map used, and "aux" if an auxiliary classifier
is used.
classifier (nn.Module): module that takes the "out" element returned from
the backbone and returns a dense prediction.
aux_classifier (nn.Module, optional): auxiliary classifier used during training
"""
pass
class FCNHead(nn.Sequential):
def __init__(self, in_channels: int, channels: int) -> None:
inter_channels = in_channels // 4
layers = [
nn.Conv2d(in_channels, inter_channels, 3, padding=1, bias=False),
nn.BatchNorm2d(inter_channels),
nn.ReLU(),
nn.Dropout(0.1),
nn.Conv2d(inter_channels, channels, 1),
]
super().__init__(*layers)
_COMMON_META = {
"categories": _VOC_CATEGORIES,
"min_size": (1, 1),
"_docs": """
These weights were trained on a subset of COCO, using only the 20 categories that are present in the Pascal VOC
dataset.
""",
}
class FCN_ResNet50_Weights(WeightsEnum):
COCO_WITH_VOC_LABELS_V1 = Weights(
url="https://download.pytorch.org/models/fcn_resnet50_coco-1167a1af.pth",
transforms=partial(SemanticSegmentation, resize_size=520),
meta={
**_COMMON_META,
"num_params": 35322218,
"recipe": "https://github.com/pytorch/vision/tree/main/references/segmentation#fcn_resnet50",
"_metrics": {
"COCO-val2017-VOC-labels": {
"miou": 60.5,
"pixel_acc": 91.4,
}
},
"_ops": 152.717,
"_file_size": 135.009,
},
)
DEFAULT = COCO_WITH_VOC_LABELS_V1
class FCN_ResNet101_Weights(WeightsEnum):
COCO_WITH_VOC_LABELS_V1 = Weights(
url="https://download.pytorch.org/models/fcn_resnet101_coco-7ecb50ca.pth",
transforms=partial(SemanticSegmentation, resize_size=520),
meta={
**_COMMON_META,
"num_params": 54314346,
"recipe": "https://github.com/pytorch/vision/tree/main/references/segmentation#deeplabv3_resnet101",
"_metrics": {
"COCO-val2017-VOC-labels": {
"miou": 63.7,
"pixel_acc": 91.9,
}
},
"_ops": 232.738,
"_file_size": 207.711,
},
)
DEFAULT = COCO_WITH_VOC_LABELS_V1
def _fcn_resnet(
backbone: ResNet,
num_classes: int,
aux: Optional[bool],
) -> FCN:
return_layers = {"layer4": "out"}
if aux:
return_layers["layer3"] = "aux"
backbone = IntermediateLayerGetter(backbone, return_layers=return_layers)
aux_classifier = FCNHead(1024, num_classes) if aux else None
classifier = FCNHead(2048, num_classes)
return FCN(backbone, classifier, aux_classifier)
@register_model()
@handle_legacy_interface(
weights=("pretrained", FCN_ResNet50_Weights.COCO_WITH_VOC_LABELS_V1),
weights_backbone=("pretrained_backbone", ResNet50_Weights.IMAGENET1K_V1),
)
def fcn_resnet50(
*,
weights: Optional[FCN_ResNet50_Weights] = None,
progress: bool = True,
num_classes: Optional[int] = None,
aux_loss: Optional[bool] = None,
weights_backbone: Optional[ResNet50_Weights] = ResNet50_Weights.IMAGENET1K_V1,
**kwargs: Any,
) -> FCN:
"""Fully-Convolutional Network model with a ResNet-50 backbone from the `Fully Convolutional
Networks for Semantic Segmentation <https://arxiv.org/abs/1411.4038>`_ paper.
.. betastatus:: segmentation module
Args:
weights (:class:`~torchvision.models.segmentation.FCN_ResNet50_Weights`, optional): The
pretrained weights to use. See
:class:`~torchvision.models.segmentation.FCN_ResNet50_Weights` 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.
num_classes (int, optional): number of output classes of the model (including the background).
aux_loss (bool, optional): If True, it uses an auxiliary loss.
weights_backbone (:class:`~torchvision.models.ResNet50_Weights`, optional): The pretrained
weights for the backbone.
**kwargs: parameters passed to the ``torchvision.models.segmentation.fcn.FCN``
base class. Please refer to the `source code
<https://github.com/pytorch/vision/blob/main/torchvision/models/segmentation/fcn.py>`_
for more details about this class.
.. autoclass:: torchvision.models.segmentation.FCN_ResNet50_Weights
:members:
"""
weights = FCN_ResNet50_Weights.verify(weights)
weights_backbone = ResNet50_Weights.verify(weights_backbone)
if weights is not None:
weights_backbone = None
num_classes = _ovewrite_value_param("num_classes", num_classes, len(weights.meta["categories"]))
aux_loss = _ovewrite_value_param("aux_loss", aux_loss, True)
elif num_classes is None:
num_classes = 21
backbone = resnet50(weights=weights_backbone, replace_stride_with_dilation=[False, True, True])
model = _fcn_resnet(backbone, num_classes, aux_loss)
if weights is not None:
model.load_state_dict(weights.get_state_dict(progress=progress, check_hash=True))
return model
@register_model()
@handle_legacy_interface(
weights=("pretrained", FCN_ResNet101_Weights.COCO_WITH_VOC_LABELS_V1),
weights_backbone=("pretrained_backbone", ResNet101_Weights.IMAGENET1K_V1),
)
def fcn_resnet101(
*,
weights: Optional[FCN_ResNet101_Weights] = None,
progress: bool = True,
num_classes: Optional[int] = None,
aux_loss: Optional[bool] = None,
weights_backbone: Optional[ResNet101_Weights] = ResNet101_Weights.IMAGENET1K_V1,
**kwargs: Any,
) -> FCN:
"""Fully-Convolutional Network model with a ResNet-101 backbone from the `Fully Convolutional
Networks for Semantic Segmentation <https://arxiv.org/abs/1411.4038>`_ paper.
.. betastatus:: segmentation module
Args:
weights (:class:`~torchvision.models.segmentation.FCN_ResNet101_Weights`, optional): The
pretrained weights to use. See
:class:`~torchvision.models.segmentation.FCN_ResNet101_Weights` 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.
num_classes (int, optional): number of output classes of the model (including the background).
aux_loss (bool, optional): If True, it uses an auxiliary loss.
weights_backbone (:class:`~torchvision.models.ResNet101_Weights`, optional): The pretrained
weights for the backbone.
**kwargs: parameters passed to the ``torchvision.models.segmentation.fcn.FCN``
base class. Please refer to the `source code
<https://github.com/pytorch/vision/blob/main/torchvision/models/segmentation/fcn.py>`_
for more details about this class.
.. autoclass:: torchvision.models.segmentation.FCN_ResNet101_Weights
:members:
"""
weights = FCN_ResNet101_Weights.verify(weights)
weights_backbone = ResNet101_Weights.verify(weights_backbone)
if weights is not None:
weights_backbone = None
num_classes = _ovewrite_value_param("num_classes", num_classes, len(weights.meta["categories"]))
aux_loss = _ovewrite_value_param("aux_loss", aux_loss, True)
elif num_classes is None:
num_classes = 21
backbone = resnet101(weights=weights_backbone, replace_stride_with_dilation=[False, True, True])
model = _fcn_resnet(backbone, num_classes, aux_loss)
if weights is not None:
model.load_state_dict(weights.get_state_dict(progress=progress, check_hash=True))
return model
|