o #j>@s"ddlZddlZddlmZddlmZddlmZmZmZm Z m Z m Z m Z ddl mZddlmZgZddd d d d ZGd ddejZGdddejZGdddejZGdddejZGdddejZGdddejZddZd&ddZd&ddZd&d d!Zd&d"d#Zd&d$d%ZdS)'N)nn) ParamAttr)AdaptiveAvgPool2D AvgPool2D BatchNormConv2DDropoutLinear MaxPool2D)Uniform)get_weights_path_from_url)zYhttps://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DenseNet121_pretrained.pdparamsZ db1b239ed80a905290fd8b01d3af08e4)zYhttps://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DenseNet161_pretrained.pdparamsZ 62158869cb315098bd25ddbfd308a853)zYhttps://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DenseNet169_pretrained.pdparamsZ 82cc7c635c3f19098c748850efb2d796)zYhttps://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DenseNet201_pretrained.pdparamsZ 16ca29565a7712329cf9e36e02caaf58)zYhttps://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DenseNet264_pretrained.pdparamsZ 3270ce516b85370bba88cfdd9f60bff4) densenet121 densenet161 densenet169 densenet201 densenet264c.eZdZ    dfdd ZddZZS) BNACConvLayerrreluc s8tt||d|_t||||||tdd|_dS)NactFZ in_channelsZ out_channels kernel_sizestridepaddinggroups weight_attr bias_attr)super__init__r _batch_normrr_convself num_channels num_filters filter_sizerpadrr __class__^/var/www/html/Deteccion_Ine/venv/lib/python3.10/site-packages/paddle/vision/models/densenet.pyr ;s  zBNACConvLayer.__init__cC||}||}|SN)r!r"r$inputyr+r+r,forwardS  zBNACConvLayer.forwardrrrr__name__ __module__ __qualname__r r2 __classcell__r+r+r)r,r:rc$eZdZfddZddZZS) DenseLayercsZt||_t|||dddd|_t|||dddd|_|r+t|dd|_dSdS)Nrrr%r&r'r(rZdownscale_in_infer)pmode)rr dropoutr bn_ac_func1 bn_ac_func2r dropout_func)r$r% growth_ratebn_sizerAr)r+r,r Zs& zDenseLayer.__init__cCs:||}||}|jr||}tj||gdd}|S)Nr)Zaxis)rBrCrArDpaddleconcat)r$r0convr+r+r,r2qs   zDenseLayer.forwardr5r+r+r)r,r<Ys r<cs(eZdZ dfdd ZddZZS) DenseBlockNc sbt||_g|_|}t|D]}|j||d|dt||||d||}qdS)N_r)r%rErFrA)rr rAdense_layer_funcrangeappend add_sublayerr<) r$r% num_layersrFrErAnameZ pre_channellayerr)r+r,r {s$   zDenseBlock.__init__cCs|}|jD]}||}q|Sr.)rL)r$r0rIfuncr+r+r,r2s  zDenseBlock.forwardr.r5r+r+r)r,rJzsrJcr;)TransitionLayercs2tt||dddd|_tdddd|_dS)Nrrr=rrr)rr r conv_ac_funcr pool2d_avg)r$r%num_output_featuresr)r+r,r s zTransitionLayer.__init__cCr-r.)rWrXr/r+r+r,r2r3zTransitionLayer.forwardr5r+r+r)r,rTs  rTcr) ConvBNLayerrrrc s8tt||||||tdd|_t||d|_dS)NFrr)rr rrr"rr!r#r)r+r,r s  zConvBNLayer.__init__cCr-r.)r"r!r/r+r+r,r2r3zConvBNLayer.forwardr4r5r+r+r)r,rZr:rZcs4eZdZdZ     d fdd Zd d ZZS) DenseNetaDenseNet model from `"Densely Connected Convolutional Networks" `_. Args: layers (int, optional): Layers of DenseNet. Default: 121. bn_size (int, optional): Expansion of growth rate in the middle layer. Default: 4. dropout (float, optional): Dropout rate. Default: :math:`0.0`. 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 DenseNet model. Examples: .. code-block:: python >>> import paddle >>> from paddle.vision.models import DenseNet >>> # Build model >>> densenet = DenseNet() >>> x = paddle.rand([1, 3, 224, 224]) >>> out = densenet(x) >>> print(out.shape) [1, 1000] yTcst||_||_gd}||vsJd|d|ddgdfddgd fddgd fddgd fddgd fd}||\}} } td |ddd dd|_td ddd|_| |_g|_ g|_ |} |} t | D]O\} }|j | d| dt| ||| |dt| dd| || } | } | t| dkr|j | d| ddt| | dd| d} | d} qit| dd|_|jrtd|_|jdkrdt| d}t| |tt| |dtd|_dSdS)N)r\zsupported layers are z but input layer is @ ) `0)rfrg$rh)rfrgrere)rfrgrkre)rfrgrdrkr>rUr)r%r&r'rr(rrrVZdb_conv_rI)r%rPrFrErArQZtr_convZ_blk)r%rYrrg?)Z initializer)rr)rr num_classes with_poolrZ conv1_funcr pool2d_max block_configdense_block_func_listtransition_func_list enumeraterNrOrJstrlenrTr batch_normrrXmathsqrtr rr out)r$layersrFrArnroZsupported_layersZ densenet_specZnum_init_featuresrErrZpre_num_channelsZ num_featuresirPZstdvr)r+r,r s             zDenseNet.__init__cCs||}||}t|jD]\}}|j||}|t|jdkr*|j||}q||}|jr8| |}|j dkrJt j |ddd}| |}|S)Nrr)Z start_axisZ stop_axis)rprqrurrrsrwrtrxrorXrnrGflattenr{)r$r0rIr}rPr1r+r+r,r2<s      zDenseNet.forward)r\r]r^r_T)r6r7r8__doc__r r2r9r+r+r)r,r[s Rr[cKs^tdd|i|}|r-|tvsJ|dtt|dt|d}t|}|||S)Nr|zJ model do not have a pretrained model now, you should set pretrained=Falserrr+)r[ model_urlsr rGloadZset_dict)archr| pretrainedkwargsmodelZ weight_pathparamr+r+r, _densenetQs   rFcKtdd|fi|S)aDenseNet 121-layer model from `"Densely Connected Convolutional 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:`DenseNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of DenseNet 121-layer model. Examples: .. code-block:: python >>> import paddle >>> from paddle.vision.models import densenet121 >>> # Build model >>> model = densenet121() >>> # Build model and load imagenet pretrained weight >>> # model = densenet121(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) [1, 1000] r r\rrrr+r+r,r ar cKr)aDenseNet 161-layer model from `"Densely Connected Convolutional 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:`DenseNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of DenseNet 161-layer model. Examples: .. code-block:: python >>> import paddle >>> from paddle.vision.models import densenet161 >>> # Build model >>> model = densenet161() >>> # Build model and load imagenet pretrained weight >>> # model = densenet161(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) [1, 1000] rr`rrr+r+r,rrrcKr)aDenseNet 169-layer model from `"Densely Connected Convolutional 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:`DenseNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of DenseNet 169-layer model. Examples: .. code-block:: python >>> import paddle >>> from paddle.vision.models import densenet169 >>> # Build model >>> model = densenet169() >>> # Build model and load imagenet pretrained weight >>> # model = densenet169(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) [1, 1000] rrarrr+r+r,rrrcKr)aDenseNet 201-layer model from `"Densely Connected Convolutional 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:`DenseNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of DenseNet 201-layer model. Examples: .. code-block:: python >>> import paddle >>> from paddle.vision.models import densenet201 >>> # Build model >>> model = densenet201() >>> # Build model and load imagenet pretrained weight >>> # model = densenet201(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) [1, 1000] rrbrrr+r+r,rsrcKr)aDenseNet 264-layer model from `"Densely Connected Convolutional 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:`DenseNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of DenseNet 264-layer model. Examples: .. code-block:: python >>> import paddle >>> from paddle.vision.models import densenet264 >>> # Build model >>> model = densenet264() >>> # Build model and load imagenet pretrained weight >>> # model = densenet264(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) [1, 1000] rrcrrr+r+r,rrr)F) ryrGrZpaddle.base.param_attrrZ paddle.nnrrrrrr r Zpaddle.nn.initializerr Zpaddle.utils.downloadr __all__rZLayerrr<rJrTrZr[rr rrrrr+r+r+r,s6  $ !  ! ! !