ёin%SSKJr SSKJrJr SSKrSSKJr SSKJr \(a,SSKJ r J r SSK J r J r SSKJr SS KJr \ S r"S S \ 5r/rS SSSSSSSSSSSSS . rS\S'"SS\R,5r"SS\R,5r"S S!\R,5rS0S"jrS1S2S#jjrS1S3S$jjrS1S3S%jjrS1S3S&jjrS1S3S'jjrS1S3S(jjr S1S3S)jjr!S1S3S*jjr"S1S3S+jjr#S1S3S,jjr$S1S3S-jjr%S1S3S.jjr&S1S3S/jjr'g)4) annotations) TYPE_CHECKINGCallableN)nn)get_weights_path_from_url)Literal TypedDict) NotRequiredUnpack)Tensor)Size2) resnet18resnet34resnet50 resnet101 resnet152resnext50_32x4dresnext50_64x4dresnext101_32x4dresnext101_64x4dresnext152_32x4dresnext152_64x4dwide_resnet50_2wide_resnet101_2c>\rSrSr%S\S'S\S'S\S'S\S'Srg ) _ResNetOptions.zNotRequired[int]width num_classeszNotRequired[bool] with_poolgroupsN)__name__ __module__ __qualname____firstlineno____annotations____static_attributes__r"[/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/vision/models/resnet.pyrr.s%%$$  r)r)z:https://paddle-hapi.bj.bcebos.com/models/resnet18.pdparams cf548f46534aa3560945be4b95cd11c4)z:https://paddle-hapi.bj.bcebos.com/models/resnet34.pdparams 8d2275cf8706028345f78ac0e1d31969)z:https://paddle-hapi.bj.bcebos.com/models/resnet50.pdparams ca6f485ee1ab0492d38f323885b0ad80)z;https://paddle-hapi.bj.bcebos.com/models/resnet101.pdparams 02f35f034ca3858e1e54d4036443c92d)z;https://paddle-hapi.bj.bcebos.com/models/resnet152.pdparams 7ad16a2f1e7333859ff986138630fd7a)zAhttps://paddle-hapi.bj.bcebos.com/models/resnext50_32x4d.pdparams dc47483169be7d6f018fcbb7baf8775d)zAhttps://paddle-hapi.bj.bcebos.com/models/resnext50_64x4d.pdparams 063d4b483e12b06388529450ad7576db)zBhttps://paddle-hapi.bj.bcebos.com/models/resnext101_32x4d.pdparams 967b090039f9de2c8d06fe994fb9095f)zBhttps://paddle-hapi.bj.bcebos.com/models/resnext101_64x4d.pdparams 98e04e7ca616a066699230d769d03008)zBhttps://paddle-hapi.bj.bcebos.com/models/resnext152_32x4d.pdparams 18ff0beee21f2efc99c4b31786107121)zBhttps://paddle-hapi.bj.bcebos.com/models/resnext152_64x4d.pdparams 77c4af00ca42c405fa7f841841959379)zAhttps://paddle-hapi.bj.bcebos.com/models/wide_resnet50_2.pdparams 0282f804d73debdab289bd9fea3fa6dc)zBhttps://paddle-hapi.bj.bcebos.com/models/wide_resnet101_2.pdparams d4360a2d23657f059216f5d5a1a9ac93zdict[str, tuple[str, str]] model_urlscx^\rSrSr%SrS\S'SS U4SjjjrS SjrSrU=r $) BasicBlockoint expansionc \>[T U]5 Uc[RnUS:a [ S5e[R "XSSUSS9UlU"U5Ul[R"5Ul [R "X"SSSS9Ul U"U5Ul X@l X0l g)Nr<z(Dilation > 1 not supported in BasicBlockF)paddingstride bias_attr)rArC)super__init__r BatchNorm2DNotImplementedErrorConv2Dconv1bn1ReLUreluconv2bn2 downsamplerB) selfinplanesplanesrBrOr! base_widthdilation norm_layer __class__s r*rEBasicBlock.__init__rs   /1~~J a<%: YY a6U  f%GGI YYvq!uM f%$ r)cUnURU5nURU5nURU5nURU5nUR U5nUR bUR U5nX2- nURU5nU$N)rIrJrLrMrNrOrPxidentityouts r*forwardBasicBlock.forwardsyjjmhhsmiinjjohhsm ?? &q)H iin r))rJrNrIrMrOrLrBr<Nr<@r<NrQr=rRr=rBr rOznn.Layer | Noner!r=rSr=rTr=rUzCallable[..., nn.Layer] | NonereturnNoner[r rcr r#r$r%r&r>r'rEr^r( __classcell__rVs@r*r:r:osIs &*59  $   3 <r)r:cx^\rSrSr%SrS\S'SS U4SjjjrS SjrSrU=r $) BottleneckBlockr=r>c >[T U]5 Uc[Rn[ X&S- -5U-n [R "XSSS9UlU"U 5Ul[R "U U SUUUUSS9UlU"U 5Ul [R "XUR-SSS9Ul U"X R-5Ul [R"5UlX@lX0lg)NgP@r<F)rCr@)rArBr!rTrC)rDrErrFr=rHrIrJrMrNr>conv3bn3rKrLrOrB) rPrQrRrBrOr!rSrTrUrrVs r*rEBottleneckBlock.__init__s   JF4/01F:YYxUC e$YY      e$YY DNN*A  f~~56GGI $ r)cUnURU5nURU5nURU5nURU5nUR U5nURU5nUR U5nUR U5nURbURU5nX2- nURU5nU$rY)rIrJrLrMrNrnrorOrZs r*r^BottleneckBlock.forwardsjjmhhsmiinjjohhsmiinjjohhsm ?? &q)H iin r)) rJrNrorIrMrnrOrLrBr`rbrerfrhs@r*rjrjsIs &*59%%% % $ %  %%%3% %%Nr)rjc^\rSrSr%SrS\S'S\S'S\S'S\S'S\S 'S\S 'SSU4S jjjrSSS jjrSS jrSr U=r $)ResNetaResNet model from `"Deep Residual Learning for Image Recognition" `_. Args: Block (BasicBlock|BottleneckBlock): Block module of model. depth (int, optional): Layers of ResNet, Default: 50. width (int, optional): Base width per convolution group for each convolution block, Default: 64. 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 fc layer or not. Default: True. groups (int, optional): Number of groups for each convolution block, Default: 1. Returns: :ref:`api_paddle_nn_Layer`. An instance of ResNet model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import ResNet >>> from paddle.vision.models.resnet import ( ... BottleneckBlock, ... BasicBlock, ... ) >>> # build ResNet with 18 layers >>> resnet18 = ResNet(BasicBlock, 18) >>> # build ResNet with 50 layers >>> resnet50 = ResNet(BottleneckBlock, 50) >>> # build Wide ResNet model >>> wide_resnet50_2 = ResNet(BottleneckBlock, 50, width=64 * 2) >>> # build ResNeXt model >>> resnext50_32x4d = ResNet(BottleneckBlock, 50, width=4, groups=32) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = resnet18(x) >>> print(out.shape) paddle.Size([1, 1000]) r=r!rSrboolr rQrTc 4>[T U]5 /SQ/SQ/SQ/SQ/SQS.nXrnX`lX0lX@lXPl[ RUlSUl SUl [ R"SURS S SS S 9Ul URUR5Ul [ R"5Ul[ R "SS SS 9UlUR%USUS5UlUR%USUSS S9UlUR%USUS S S9UlUR%USUSS S9UlU(a[ R."S5UlUS:a*[ R2"SUR4-U5Ulgg)N)rxrxrx)r@rlr@)r@rlr@)r@$r@)"2erar<r@rxF) kernel_sizerBrArC)rrBrAr)rBi)r<r<)rDrEr!rSrr rrF _norm_layerrQrTrHrIrJrKrL MaxPool2Dmaxpool _make_layerlayer1layer2layer3layer4AdaptiveAvgPool2DavgpoolLinearr>fc) rPblockdepthrrr r! layer_cfglayersrVs r*rEResNet.__init__sq   ! &">>  YY MM   ##DMM2GGI ||!QG &&ub&)< &&uc6!9Q&G &&uc6!9Q&G &&uc6!9Q&G //7DL ?iieoo 5{CDG r)c URnSnURnU(aU=RU-slSnUS:wdURX!R-:waU[R "[R "URX!R-SUSS9U"X!R-55n/n U RU"URUUUURURUU55 X!R-Ul[SU5H:n U RU"URUURURUS95 M< [R "U 6$)Nr<F)rBrC)r!rSrU) rrTrQr>r SequentialrHappendr!rSrange) rPrrRblocksrBdilaterUrOprevious_dilationr_s r*rResNet._make_layerHs2%%   MM  MMV #MF Q;$--6OO+CC MM__,!# 6OO34 J   !  0 q&!A MMMM;;#)  "}}f%%r)cURU5nURU5nURU5nURU5nUR U5nUR U5nUR U5nURU5nUR(aURU5nURS:a([R"US5nURU5nU$)Nrr<)rIrJrLrrrrrr rrpaddleflattenr)rPr[s r*r^ResNet.forward}s JJqM HHQK IIaL LLO KKN KKN KKN KKN >> QA   a q!$A Ar))rrrSrJrIrTrr!rQrrrrrrrLr )rraiTr<)r"type[BasicBlock | BottleneckBlock]rr=rr=rr=r rvr!r=rcrd)r<F) rrrRr=rr=rBr=rrvrcz nn.Sequentialre) r#r$r%r&__doc__r'rErr^r(rgrhs@r*rtrts*X KOOMM .D1.D.D .D  .D  .D.D .D.Dj 3&13&3& 3&  3&  3& 3&jr)rtc [X40UD6nU(a[U[;d US35e[[US[US5n[R"U5nUR U5 U$)NzJ model do not have a pretrained model now, you should set pretrained=Falserr<)rtr8rrloadset_dict)archBlockr pretrainedkwargsmodel weight_pathparams r*_resnetrs| 5 *6 *Ez! f^ _ !0 t Q D!1!!4  K( u Lr)c ([S[SU40UD6$)aResNet 18-layer model from `"Deep Residual Learning for Image Recognition" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ResNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ResNet 18-layer model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import resnet18 >>> # build model >>> model = resnet18() >>> # build model and load imagenet pretrained weight >>> # model = resnet18(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rr}rr:rrs r*rrs< :z2z DV DDr)c ([S[SU40UD6$)aResNet 34-layer model from `"Deep Residual Learning for Image Recognition" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ResNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ResNet 34-layer model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import resnet34 >>> # build model >>> model = resnet34() >>> # build model and load imagenet pretrained weight >>> # model = resnet34(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rr~rrs r*rrs@ :z2z DV DDr)c ([S[SU40UD6$)aResNet 50-layer model from `"Deep Residual Learning for Image Recognition" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ResNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ResNet 50-layer model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import resnet50 >>> # build model >>> model = resnet50() >>> # build model and load imagenet pretrained weight >>> # model = resnet50(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rrrrjrs r*rrs@ :J I& IIr)c ([S[SU40UD6$)aResNet 101-layer model from `"Deep Residual Learning for Image Recognition" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ResNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ResNet 101-layer. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import resnet101 >>> # build model >>> model = resnet101() >>> # build model and load imagenet pretrained weight >>> # model = resnet101(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rrrrs r*rr@ ;j KF KKr)c ([S[SU40UD6$)aResNet 152-layer model from `"Deep Residual Learning for Image Recognition" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ResNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ResNet 152-layer model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import resnet152 >>> # build model >>> model = resnet152() >>> # build model and load imagenet pretrained weight >>> # model = resnet152(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rrrrs r*rr1rr)c <SUS'SUS'[S[SU40UD6$)aResNeXt-50 32x4d model from `"Aggregated Residual Transformations for Deep Neural Networks" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ResNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ResNeXt-50 32x4d model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import resnext50_32x4d >>> # build model >>> model = resnext50_32x4d() >>> # build model and load imagenet pretrained weight >>> # model = resnext50_32x4d(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) r!rlrrrrrs r*rrT/@F8F7O $or: P PPr)c <SUS'SUS'[S[SU40UD6$)aResNeXt-50 64x4d model from `"Aggregated Residual Transformations for Deep Neural Networks" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ResNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ResNeXt-50 64x4d model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import resnext50_64x4d >>> # build model >>> model = resnext50_64x4d() >>> # build model and load imagenet pretrained weight >>> # model = resnext50_64x4d(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rar!rlrrrrrs r*rryrr)c <SUS'SUS'[S[SU40UD6$)aResNeXt-101 32x4d model from `"Aggregated Residual Transformations for Deep Neural Networks" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ResNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ResNeXt-101 32x4d model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import resnext101_32x4d >>> # build model >>> model = resnext101_32x4d() >>> # build model and load imagenet pretrained weight >>> # model = resnext101_32x4d(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rr!rlrrrrrs r*rr6@F8F7O OS* @F r)c <SUS'SUS'[S[SU40UD6$)aResNeXt-101 64x4d model from `"Aggregated Residual Transformations for Deep Neural Networks" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ResNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ResNeXt-101 64x4d model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import resnext101_64x4d >>> # build model >>> model = resnext101_64x4d() >>> # build model and load imagenet pretrained weight >>> # model = resnext101_64x4d(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rar!rlrrrrrs r*rrrr)c <SUS'SUS'[S[SU40UD6$)aResNeXt-152 32x4d model from `"Aggregated Residual Transformations for Deep Neural Networks" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ResNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ResNeXt-152 32x4d model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import resnext152_32x4d >>> # build model >>> model = resnext152_32x4d() >>> # build model and load imagenet pretrained weight >>> # model = resnext152_32x4d(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rr!rlrrrrrs r*rrrr)c <SUS'SUS'[S[SU40UD6$)aResNeXt-152 64x4d model from `"Aggregated Residual Transformations for Deep Neural Networks" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ResNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ResNeXt-152 64x4d model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import resnext152_64x4d >>> # build model >>> model = resnext152_64x4d() >>> # build model and load imagenet pretrained weight >>> # model = resnext152_64x4d(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rar!rlrrrrrs r*rrrr)c 2SUS'[S[SU40UD6$)aWide ResNet-50-2 model from `"Wide Residual Networks" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ResNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of Wide ResNet-50-2 model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import wide_resnet50_2 >>> # build model >>> model = wide_resnet50_2() >>> # build model and load imagenet pretrained weight >>> # model = wide_resnet50_2(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rrrrrrs r*rr:s%@F7O $or: P PPr)c 2SUS'[S[SU40UD6$)aWide ResNet-101-2 model from `"Wide Residual Networks" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ResNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of Wide ResNet-101-2 model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import wide_resnet101_2 >>> # build model >>> model = wide_resnet101_2() >>> # build model and load imagenet pretrained weight >>> # model = wide_resnet101_2(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rrrrrrs r*rr^s,@F7O OS* @F r)) r _ResNetArchrrrr=rrvrUnpack[_ResNetOptions]rcrt)F)rrrcrt)rrvrrrcrt)( __future__rtypingrrrrpaddle.utils.downloadrrr typing_extensionsr r r paddle._typingr rr__all__r8r'Layerr:rjrtrrrrrrrrrrrrrrr"r)r*rs#* ;)5$ K !! c5* &5p11h>bhh>BjRXXjZ  -   %   ,ED E E(> E  EH J J(> J  JH L L(> L  LH L L(> L  LH"Q"Q(>"Q "QL"Q"Q(>"Q "QL$$(>$ $P$$(>$ $P$$(>$ $P$$(>$ $P!Q!Q(>!Q !QJ##(># #r)