o #jM@sddlZddlmZddlmZmZmZddlmZddlm Z gZ ddd d d d d dZ ddZ ddZ GdddejZGdddejZGdddejZd*ddZd*ddZd*ddZd*d d!Zd*d"d#Zd*d$d%Zd*d&d'Zd*d(d)ZdS)+N)nn)AdaptiveAvgPool2DLinear MaxPool2D)get_weights_path_from_url)ConvNormActivation)zEhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_x0_25.pdparamsZ 1e509b4c140eeb096bb16e214796d03b)zEhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_x0_33.pdparamsZ 3d7b3ab0eaa5c0927ff1026d31b729bd)zDhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_x0_5.pdparamsZ 5e5cee182a7793c4e4c73949b1a71bd4)zDhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_x1_0.pdparamsZ 122d42478b9e81eb49f8a9ede327b1a4)zDhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_x1_5.pdparamsZ faced5827380d73531d0ee027c67826d)zDhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_x2_0.pdparamsZ cd3dddcd8305e7bcd8ad14d1c69a5784)zEhttps://paddle-hapi.bj.bcebos.com/models/shufflenet_v2_swish.pdparamsZ adde0aa3b023e5b0c94a68be1c394b84)shufflenet_v2_x0_25shufflenet_v2_x0_33shufflenet_v2_x0_5shufflenet_v2_x1_0shufflenet_v2_x1_5shufflenet_v2_x2_0shufflenet_v2_swishcCs6|dkrtjS|dkrtjS|durdStd|)Nswishreluz*The activation function is not supported: )rZSwishReLU RuntimeError)actrb/var/www/html/Deteccion_Ine/venv/lib/python3.10/site-packages/paddle/vision/models/shufflenetv2.pycreate_activation_layer8srcCsb|jdd\}}}}||}tj||||||gd}tj|gdd}tj|||||gd}|S)Nr)shape)rrr)perm)rpaddleZreshapeZ transpose)xgroupsZ batch_sizeZ num_channelsheightwidthZchannels_per_grouprrrchannel_shuffleCsr"c*eZdZejffdd ZddZZS)InvertedResidualc srtt|d|ddddd|d|_t|d|dd|d|ddd|_t|d|ddddd|d|_dS)Nrrr in_channels out_channels kernel_sizestridepaddingractivation_layerr)super__init__r_conv_pw_conv_dw _conv_linearselfr&r'r)r+ __class__rrr-Us8    zInvertedResidual.__init__cCsftj||jdd|jddgdd\}}||}||}||}tj||gdd}t|dS)Nrr)Znum_or_sectionsaxisr5)rsplitrr.r/r0concatr"r2inputsx1Zx2outrrrforwardus    zInvertedResidual.forward__name__ __module__ __qualname__rrr-r= __classcell__rrr3rr$Ts r$cr#)InvertedResidualDSc stt||d|d|dd|_t||ddddd|d|_t||ddddd|d|_t|d|dd|d|ddd|_t|d|ddddd|d|_dS)Nrrr%rr)r,r-r _conv_dw_1_conv_linear_1 _conv_pw_2 _conv_dw_2_conv_linear_2r1r3rrr-s\      zInvertedResidualDS.__init__cCsN||}||}||}||}||}tj||gdd}t|dS)Nrr6r)rDrErFrGrHrr8r"r9rrrr=s      zInvertedResidualDS.forwardr>rrr3rrCs5rCcs*eZdZdZd fdd Zdd ZZS) ShuffleNetV2aShuffleNetV2 model from `"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design" `_. Args: scale (float, optional): Scale of output channels. Default: True. act (str, optional): Activation function of neural network. Default: "relu". num_classes (int, optional): Output dim of last fc layer. If num_classes <= 0, last fc layer will not be defined. Default: 1000. with_pool (bool, optional): Use pool before the last fc layer or not. Default: True. Returns: :ref:`api_paddle_nn_Layer`. An instance of ShuffleNetV2 model. Examples: .. code-block:: python >>> import paddle >>> from paddle.vision.models import ShuffleNetV2 >>> shufflenet_v2_swish = ShuffleNetV2(scale=1.0, act="swish") >>> x = paddle.rand([1, 3, 224, 224]) >>> out = shufflenet_v2_swish(x) >>> print(out.shape) [1, 1000] ?rTc st||_||_||_gd}t|}|dkrgd}n7|dkr(gd}n.|dkr1gd}n%|dkr:gd }n|d krCgd }n|d krLgd }n tdt|dtd|dddd|d|_ t dddd|_ g|_ t |D]X\}} t| D]O} | dkr|jt||d||dd|dt|ddt| dd} n!|jt||d||dd|dt|ddt| dd} |j | qzqrt|d|dddd|d|_|rtd|_|dkr|d|_t|d||_dSdS)N)rr?)rO0`Q?)rNrO @rR?)rNrOrPrQrJ)rNrOtirY?)rNrOi`irY@)rNrOiiizThis scale size:[z] is not implemented!rrr)r&r'r(r)r*r+)r(r)r*r)r&r'r)r+_)ZsublayernamerN)r,r-scale num_classes with_poolrNotImplementedErrorstrr_conv1r _max_pool _block_list enumeraterangeZ add_sublayerrCr$append _last_convr _pool2d_avgZ_out_cr_fc) r2rcrrdreZ stage_repeatsr+Zstage_out_channelsZstage_idZ num_repeatiblockr3rrr-s                zShuffleNetV2.__init__cCsj||}||}|jD]}||}q ||}|jr!||}|jdkr3tj|ddd}| |}|S)NrrrN)Z start_axisZ stop_axis) rhrirjrnrerordrflattenrp)r2r:rinvrrrr=,s        zShuffleNetV2.forward)rJrrKT)r?r@rA__doc__r-r=rBrrr3rrIsNrIFcKsZtdi|}|r+|tvsJ|dtt|dt|d}t|}|||S)NzJ model do not have a pretrained model now, you should set pretrained=Falserrr)rI model_urlsrrloadZset_dict)arch pretrainedkwargsmodelZ weight_pathparamrrr_shufflenet_v2<s   r}cKt dd|d|S)aRShuffleNetV2 with 0.25x output channels, as described in `"ShuffleNet V2: Practical Guidelines for Ecient 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:: python >>> 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) [1, 1000] r rMrcryN)r r}ryrzrrrr Kr cKr~)aRShuffleNetV2 with 0.33x output channels, as described in `"ShuffleNet V2: Practical Guidelines for Ecient 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:: python >>> 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) [1, 1000] r rSrN)r rrrrrr nrr cKr~)aMShuffleNetV2 with 0.5x output channels, as described in `"ShuffleNet V2: Practical Guidelines for Ecient 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:: python >>> 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) [1, 1000] r rWrN)r rrrrrr rr cKr~)aMShuffleNetV2 with 1.0x output channels, as described in `"ShuffleNet V2: Practical Guidelines for Ecient 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:: python >>> 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) [1, 1000] r rJrN)r rrrrrr rr cKr~)aMShuffleNetV2 with 1.5x output channels, as described in `"ShuffleNet V2: Practical Guidelines for Ecient 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:: python >>> 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) [1, 1000] r r\rN)r rrrrrr rr cKr~)aMShuffleNetV2 with 2.0x output channels, as described in `"ShuffleNet V2: Practical Guidelines for Ecient 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:: python >>> 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) [1, 1000] rr^rN)rrrrrrrrrcKst ddd|d|S)aZShuffleNetV2 with swish activation function, as described in `"ShuffleNet V2: Practical Guidelines for Ecient 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:: python >>> 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) [1, 1000] rrJr)rcrryN)rrrrrrrsr)F)rrZ paddle.nnrrrZpaddle.utils.downloadropsr__all__rvrr"ZLayerr$rCrIr}r r r r r rrrrrrs6     .A y  # # # # ##