ёiyUv%SSKJr SSKJrJr SSKrSSKJr SSKJrJ r J r SSK J r SSK Jr \(a<SS KJrJr SS KJrJr SS KJr SS KJr \S r\Sr"SS\5r"SS\5r/rSSSSSSSS .rS\S'S,SjrS-Sjr"SS\R@5r!"S S!\R@5r""S"S#\R@5r#S.S/S$jjr$S0S1S%jjr%S0S1S&jjr&S0S1S'jjr'S0S1S(jjr(S0S1S)jjr)S0S1S*jjr*S0S2S+jjr+g)3) annotations) TYPE_CHECKINGCallableN)nn)AdaptiveAvgPool2DLinear MaxPool2D)get_weights_path_from_url)ConvNormActivation)Literal TypedDict) NotRequiredUnpack)Tensor)Size2)shufflenet_v2_x0_25shufflenet_v2_x0_33shufflenet_v2_x0_5shufflenet_v2_x1_0shufflenet_v2_x1_5shufflenet_v2_x2_0shufflenet_v2_swish)reluswishc4\rSrSr%S\S'S\S'S\S'Srg ) _ShuffleNetOptions.z#NotRequired[_ActivationType | None]actNotRequired[bool] with_poolNotRequired[int] num_classesN__name__ __module__ __qualname____firstlineno____annotations____static_attributes__r$a/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/vision/models/shufflenetv2.pyrr.s 00$$%%r,rc*\rSrSr%S\S'S\S'Srg)_ShuffleNetSwishOptions3r r!r"r#r$Nr%r$r,r-r/r/3s$$%%r,r/)zEhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_x0_25.pdparams 1e509b4c140eeb096bb16e214796d03b)zEhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_x0_33.pdparams 3d7b3ab0eaa5c0927ff1026d31b729bd)zDhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_x0_5.pdparams 5e5cee182a7793c4e4c73949b1a71bd4)zDhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_x1_0.pdparams 122d42478b9e81eb49f8a9ede327b1a4)zDhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_x1_5.pdparams faced5827380d73531d0ee027c67826d)zDhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_x2_0.pdparams cd3dddcd8305e7bcd8ad14d1c69a5784)zEhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_swish.pdparams adde0aa3b023e5b0c94a68be1c394b84zdict[str, tuple[str, str]] model_urlsc~US:Xa[R$US:Xa[R$Ucg[SU35e)Nrrz*The activation function is not supported: )rSwishReLU RuntimeError)rs r-create_activation_layerr=Zs= g~xx ww GuMNNr,cURSSup#pEX1-n[R"XXXE/S9n[R"U/SQS9n[R"XX4U/S9nU$)Nr)shape)rr r?)perm)r@paddlereshape transpose)xgroups batch_size num_channelsheightwidthchannels_per_groups r-channel_shufflerNesi./ggal+Jf%/  f&H A 1A q\5 IJA Hr,cb^\rSrSr\R 4SU4SjjjrSSjrSrU=r $)InvertedResidualvc >[TU]5 [US-US-SSSSUS9Ul[US-US-SUSUS-SS9Ul[US-US-SSSSUS9Ulg)Nr rAr in_channels out_channels kernel_sizestridepaddingrHactivation_layerrB)super__init__r _conv_pw_conv_dw _conv_linearselfrTrUrWrY __class__s r-r[InvertedResidual.__init__ws *#q(%*-  +$)%*1$!  /$)%*- r,c [R"UURSS-URSS-/SS9up#URU5nUR U5nUR U5n[R "X#/SS9n[US5$)NrAr )num_or_sectionsaxisre)rDsplitr@r\r]r^concatrNr`inputsx1x2outs r-forwardInvertedResidual.forwards #\\!_16<<?a3GH  ]]2  ]]2    r "mmRH1-sA&&r,)r]r^r\ rTintrUrqrWrrYzCallable[..., nn.Layer]returnNonerjrrrr r&r'r(r)rr;r[rnr+ __classcell__ras@r-rPrPvsQ 57GG " " "  " 2 "  " " H ' 'r,rPcb^\rSrSr\R 4SU4SjjjrSSjrSrU=r $)InvertedResidualDSc >[TU]5 [UUSUSUSS9Ul[UUS-SSSSUS9Ul[UUS-SSSSUS9Ul[US-US-SUSUS-SS9Ul[US-US-SSSSUS9Ulg)NrBrArSr r)rZr[r _conv_dw_1_conv_linear_1 _conv_pw_2 _conv_dw_2_conv_linear_2r_s r-r[InvertedResidualDS.__init__s -#$! 1#%*- -#%*- -$)%*1$! 1$)%*- r,cURU5nURU5nURU5nURU5nUR U5n[ R "X#/SS9n[US5$)NrArfr )r|r}r~rrrDrhrNris r-rnInvertedResidualDS.forwardsk __V $   $ __V $ __R    $mmRH1-sA&&r,)r|rr}rr~rprtrurws@r-ryrysQ 57GG 7 7 7  7 2 7  7 7 r''r,rycx^\rSrSr%SrS\S'S\S'S\S'S S U4S jjjrSS jrS rU=r $) ShuffleNetV2aShuffleNetV2 model from `"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design" `_. Args: scale (float, optional): Scale of output channels. Default: True. act (str, optional): Activation function of neural network. Default: "relu". num_classes (int, optional): Output dim of last fc layer. If num_classes <= 0, last fc layer will not be defined. Default: 1000. with_pool (bool, optional): Use pool before the last fc layer or not. Default: True. Returns: :ref:`api_paddle_nn_Layer`. An instance of ShuffleNetV2 model. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import ShuffleNetV2 >>> shufflenet_v2_swish = ShuffleNetV2(scale=1.0, act="swish") >>> x = paddle.rand([1, 3, 224, 224]) >>> out = shufflenet_v2_swish(x) >>> print(out.shape) paddle.Size([1, 1000]) floatscalerqr#boolr!c >[T U]5 XlX0lX@l/SQn[ U5nUS:Xa/SQnOQUS:Xa/SQnOFUS:Xa/SQnO;US:Xa/S QnO0US :Xa/S QnO%US :Xa/S QnO[ S[U5-S-5e[SUSSSSUS9Ul [SSSS9Ul /Ul [U5Hup[U 5Hn U S:XaCUR[!XxS-XxS-SUS9[US-5S-[U S-5-S9n OBUR[#XxS-XxS-SUS9[US-5S-[U S-5-S9n URR%U 5 M M [USUSSSSUS9UlU(a[)S5UlUS:aUSUl[/USU5Ulgg)N)r?r??)r0`Q?)rr @r?)rrrr?)rrtir?)rri`ir@)rriiizThis scale size:[z] is not implemented!rBrAr )rTrUrVrWrXrY)rVrWrXr)rTrUrWrY_)sublayernamer)rZr[rr#r!r=NotImplementedErrorstrr _conv1r _max_pool _block_list enumeraterange add_sublayerryrPappend _last_convr _pool2d_avg_out_cr_fc) r`rrr#r! stage_repeatsrYstage_out_channelsstage_id num_repeatiblockras r-r[ShuffleNetV2.__init__ s6  &"! 237 D=!:  d]!;  c\!<  c\!>  c\!>  c\!> %#c%j03JJ )+A.-   #qAF$-m$< H:&6 --!3(:a<(H);qL)I#$-= " !A.4s1q5zA.E!--!1(:a<(H);qL)I#$-= " !A.4s1q5zA.E  ''.+'%=0-*2.+B/-   03D  ?,R0DK04kBDH r,cTURU5nURU5nURH nU"U5nM URU5nUR(aUR U5nUR S:a'[R"USSS9nURU5nU$)NrrAr) start_axis stop_axis) rrrrr!rr#rDflattenr)r`rjrGinvs r-rnShuffleNetV2.forward`s KK  NN1 ##CAA$ OOA  >>  #A   a qQ"=A Ar,) rrrrrrrr#rr!)rriT) rrr_ActivationType | Noner#rqr!rrrrsrt) r&r'r(r)__doc__r*r[rnr+rvrws@r-rrs{4 LO&, RCRC$RC RC  RC  RCRCh  r,rc [SSU0UD6nU(a[U[;d US35e[[US[US5n[R"U5nUR U5 U$)NrzJ model do not have a pretrained model now, you should set pretrained=FalserrAr$)rr8r rDloadset_dict)arch pretrainedrkwargsmodel weight_pathparams r-_shufflenet_v2rps  /u / /Ez! f^ _ !0 t Q D!1!!4  K( u Lr,c  [SSUS.UD6$)aShuffleNetV2 with 0.25x output channels, as described in `"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design" `_. 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:`ShuffleNetV2 `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ShuffleNetV2 with 0.25x output channels. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import shufflenet_v2_x0_25 >>> # build model >>> model = shufflenet_v2_x0_25() >>> # build model and load imagenet pretrained weight >>> # model = shufflenet_v2_x0_25(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rrr)rrrrs r-rr'@  %)j DJ r,c  [SSUS.UD6$)aShuffleNetV2 with 0.33x output channels, as described in `"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ShuffleNetV2 `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ShuffleNetV2 with 0.33x output channels. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import shufflenet_v2_x0_33 >>> # build model >>> model = shufflenet_v2_x0_33() >>> # build model and load imagenet pretrained weight >>> # model = shufflenet_v2_x0_33(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rr)rrrs r-rrrr,c  [SSUS.UD6$)a ShuffleNetV2 with 0.5x output channels, as described in `"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design" `_. 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:`ShuffleNetV2 `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ShuffleNetV2 with 0.5x output channels. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import shufflenet_v2_x0_5 >>> # build model >>> model = shufflenet_v2_x0_5() >>> # build model and load imagenet pretrained weight >>> # model = shufflenet_v2_x0_5(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rr)rrrs r-rr'@  $'J BH r,c  [SSUS.UD6$)a ShuffleNetV2 with 1.0x output channels, as described in `"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design" `_. 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:`ShuffleNetV2 `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ShuffleNetV2 with 1.0x output channels. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import shufflenet_v2_x1_0 >>> # build model >>> model = shufflenet_v2_x1_0() >>> # build model and load imagenet pretrained weight >>> # model = shufflenet_v2_x1_0(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rr)rrrs r-rrrr,c  [SSUS.UD6$)a ShuffleNetV2 with 1.5x output channels, as described in `"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ShuffleNetV2 `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ShuffleNetV2 with 1.5x output channels. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import shufflenet_v2_x1_5 >>> # build model >>> model = shufflenet_v2_x1_5() >>> # build model and load imagenet pretrained weight >>> # model = shufflenet_v2_x1_5(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rr)rrrs r-rrrr,c  [SSUS.UD6$)a ShuffleNetV2 with 2.0x output channels, as described in `"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design" `_. 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:`ShuffleNetV2 `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ShuffleNetV2 with 2.0x output channels. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import shufflenet_v2_x2_0 >>> # build model >>> model = shufflenet_v2_x2_0() >>> # build model and load imagenet pretrained weight >>> # model = shufflenet_v2_x2_0(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rr)rrrs r-rr=rr,c "[SSSUS.UD6$)aShuffleNetV2 with swish activation function, as described in `"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`ShuffleNetV2 `. Returns: :ref:`api_paddle_nn_Layer`. An instance of ShuffleNetV2 with swish activation function. Examples: .. code-block:: pycon >>> import paddle >>> from paddle.vision.models import shufflenet_v2_swish >>> # build model >>> model = shufflenet_v2_swish() >>> # build model and load imagenet pretrained weight >>> # model = shufflenet_v2_swish(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) paddle.Size([1, 1000]) rr)rrr)rrrs r-rrbs-@        r,)rrrrznn.Layer | None)rGrrHrqrrr)Fr) r_ShuffleNetArchrrrrrUnpack[_ShuffleNetOptions]rrr)F)rrrrrrr)rrrzUnpack[_ShuffleNetSwishOptions]rrr), __future__rtypingrrrDr paddle.nnrrr paddle.utils.downloadr opsr r rtyping_extensionsrrrpaddle._typingrr_ActivationTyperr/__all__r8r*r=rNLayerrPryrrrrrrrrrr$r,r-rs #* ::;$)5$ Oo.O&Y& &)& 3* &@O "/'rxx/'dB'B'J@288@J  )   *""(B""L""(B""L""(B""L""(B""L""(B""L""(B""L&&(G&&r,