ёij*SSKJr SSKJrJrJr SSKJrJr SSK r SSK J r SSK J r \(aSSK J r SSKJrJr "S S \5r/rS S S .r"SS\ R5rSSSjjr/SQ/SQ/SQ/SQS.rSSjrSSSjjrSSSjjrSSSjjrSSSjjrg) ) annotations) TYPE_CHECKINGLiteral TypedDict) NotRequiredUnpackN)nn)get_weights_path_from_url)Tensor)Layer Sequentialc*\rSrSr%S\S'S\S'Srg) _VGGOptions!zNotRequired[int] num_classeszNotRequired[bool] with_poolN)__name__ __module__ __qualname____firstlineno____annotations____static_attributes__rX/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/vision/models/vgg.pyrr!s%%$$rr)z7https://paddle-hapi.bj.bcebos.com/models/vgg16.pdparams 89bbffc0f87d260be9b8cdc169c991c4)z7https://paddle-hapi.bj.bcebos.com/models/vgg19.pdparams 23b18bb13d8894f60f54e642be79a0dd)vgg16vgg19cd^\rSrSr%SrS\S'S\S'S S U4SjjjrS SjrS rU=r $) VGG4aVGG model from `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_. Args: features (nn.Layer): Vgg features create by function make_layers. num_classes (int, optional): Output dim of last fc layer. If num_classes <= 0, last fc layer will not be defined. Default: 1000. with_pool (bool, optional): Use pool before the last three fc layer or not. Default: True. Returns: :ref:`api_paddle_nn_Layer`. An instance of VGG model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import VGG >>> from paddle.vision.models.vgg import make_layers >>> vgg11_cfg = [ ... 64, ... 'M', ... 128, ... 'M', ... 256, ... 256, ... 'M', ... 512, ... 512, ... 'M', ... 512, ... 512, ... 'M', ... ] >>> features = make_layers(vgg11_cfg) # type: ignore >>> vgg11 = VGG(features) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = vgg11(x) >>> print(out.shape) paddle.Size([1, 1000]) intrboolrc >[TU]5 XlX lX0lU(a[ R "S5UlUS:a[ R"[ R"SS5[ R"5[ R"5[ R"SS5[ R"5[ R"5[ R"SU55Ul gg)N)r&ribi) super__init__featuresrrr AdaptiveAvgPool2Davgpoolr LinearReLUDropout classifier)selfr)rr __class__s rr( VGG.__init__fs  &" //7DL ? mm +t,   $%   $ ,DO rcURU5nUR(aURU5nURS:a([R "US5nUR U5nU$)Nr)r)rr+rpaddleflattenr/)r0xs rforward VGG.forward|sU MM!  >> QA   a q!$A"Ar)r+r/r)rr)iT)r)r rr#rr$returnNone)r7r r:r ) rrrr__doc__rr(r8r __classcell__)r1s@rr!r!4sQ,\OKO,/CG ,  rr!cR/nSnUHnUS:XaU[R"SSS9/- nM$[R"X4SSS9nU(a/X%[R"U5[R"5/- nOX%[R"5/- nUnM [R "U6$)NM) kernel_sizestrider4)rBpadding)r MaxPool2DConv2D BatchNorm2Dr-r )cfg batch_normlayers in_channelsvconv2ds r make_layersrNsFK  8 r||!<= =FYY{1aHF2>>!#4bggi@@2779--K ==& !!r) @r@r@rQr@rRr@rRrRr@)rOrOr@rPrPr@rQrQr@rRrRr@rRrRr@)rOrOr@rPrPr@rQrQrQr@rRrRrRr@rRrRrRr@)rOrOr@rPrPr@rQrQrQrQr@rRrRrRrRr@rRrRrRrRr@)ABDEc [[[UUS940UD6nU(a[U[;d US35e[ [US[US5n[ R "U5nURU5 U$)N)rIzJ model do not have a pretrained model now, you should set pretrained=Falserr4)r!rNcfgs model_urlsr r5load load_dict)archrHrI pretrainedkwargsmodel weight_pathparams r_vggrbs  DI*= H HEz! f^ _ !0 t Q D!1!!4  K(  Lrc :SnU(aUS- n[USX40UD6$)aVGG 11-layer model from `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. batch_norm (bool, optional): If True, returns a model with batch_norm layer. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`VGG `. Returns: :ref:`api_paddle_nn_Layer`. An instance of VGG 11-layer model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import vgg11 >>> # build model >>> model = vgg11() >>> # build vgg11 model with batch_norm >>> model = vgg11(batch_norm=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) vgg11_bnrSrbr]rIr^ model_names rrdrd+FJe  C B6 BBrc :SnU(aUS- n[USX40UD6$)aVGG 13-layer model from `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. batch_norm (bool): If True, returns a model with batch_norm layer. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`VGG `. Returns: :ref:`api_paddle_nn_Layer`. An instance of VGG 13-layer model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import vgg13 >>> # build model >>> model = vgg13() >>> # build vgg13 model with batch_norm >>> model = vgg13(batch_norm=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) vgg13rerTrfrgs rrkrkrirc :SnU(aUS- n[USX40UD6$)aVGG 16-layer model from `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. batch_norm (bool, optional): If True, returns a model with batch_norm layer. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`VGG `. Returns: :ref:`api_paddle_nn_Layer`. An instance of VGG 16-layer model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import vgg16 >>> # build model >>> model = vgg16() >>> # build vgg16 model with batch_norm >>> model = vgg16(batch_norm=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rrerUrfrgs rrr$rirc :SnU(aUS- n[USX40UD6$)aVGG 19-layer model from `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. batch_norm (bool, optional): If True, returns a model with batch_norm layer. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`VGG `. Returns: :ref:`api_paddle_nn_Layer`. An instance of VGG 19-layer model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import vgg19 >>> # build model >>> model = vgg19() >>> # build vgg19 model with batch_norm >>> model = vgg19(batch_norm=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rrerVrfrgs rrrMrir)F)rHzlist[int | Literal['M']]rIr$r:r ) r\strrHzLiteral['A', 'B', 'D', 'E']rIr$r]r$r^Unpack[_VGGOptions]r:r!)FF)r]r$rIr$r^ror:r!) __future__rtypingrrrtyping_extensionsrrr5r paddle.utils.downloadr r paddle.nnr r r__all__rYr!rNrXrbrdrkrrrrrrvs# 2 ;+%i%   R"((Rl7<" !"/3""&    -@  $  "   0&C&C&C"&C &CT&C&C&C"&C &CT&C&C&C"&C &CT&C&C&C"&C &Cr