o #j$@sddlZddlmmZddlmZddlmZddlmZm Z m Z m Z ddl m Z gZdddZGd d d ejZGd d d ejZGd ddejZddZdddZdddZdS)N)nn) ParamAttr)AdaptiveAvgPool2DConv2DDropout MaxPool2D)get_weights_path_from_url)z[https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SqueezeNet1_0_pretrained.pdparamsZ 30b95af60a2178f03cf9b66cd77e1db1)z[https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SqueezeNet1_1_pretrained.pdparamsZ a11250d3a1f91d7131fd095ebbf09eee) squeezenet1_0 squeezenet1_1cs&eZdZdfdd ZddZZS) MakeFireConvrcs(tt||||ttd|_dS)N)padding weight_attr bias_attr)super__init__rr_conv)selfinput_channelsZoutput_channelsZ filter_sizer  __class__`/var/www/html/Deteccion_Ine/venv/lib/python3.10/site-packages/paddle/vision/models/squeezenet.pyr%s  zMakeFireConv.__init__cCs||}t|}|S)N)rFrelu)rxrrrforward0s  zMakeFireConv.forward)r__name__ __module__ __qualname__rr __classcell__rrrrr $s r cs$eZdZfddZddZZS)MakeFirecs<tt||d|_t||d|_t||ddd|_dS)N)r )rrr r _conv_path1 _conv_path2)rrZsqueeze_channelsZexpand1x1_channelsZexpand3x3_channelsrrrr7s  zMakeFire.__init__cCs0||}||}||}tj||gddS)Nr"Zaxis)rr$r%paddleconcat)rinputsrx1Zx2rrrrEs   zMakeFire.forwardrrrrrr!6s r!cs*eZdZdZdfdd ZddZZS) SqueezeNetaSqueezeNet model from `"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size" `_. Args: version (str): Version of SqueezeNet, which can be "1.0" or "1.1". 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 SqueezeNet model. Examples: .. code-block:: python >>> import paddle >>> from paddle.vision.models import SqueezeNet >>> # build v1.0 model >>> model = SqueezeNet(version='1.0') >>> # build v1.1 model >>> # model = SqueezeNet(version='1.1') >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) [1, 1000] Tc st||_||_||_ddg}||vs Jd|d||jdkr{tddddttd |_tddd d |_ t dd d d |_ t dd d d |_ t dddd|_ t dddd|_t dddd|_t dddd|_t dd dd|_t dd dd|_nVtdd dddttd|_tddd d |_ t d d d d |_ t dd d d |_ t dddd|_ t dddd|_t dddd|_t dddd|_t dd dd|_t dd dd|_tddd|_td|dttd|_td|_dS)N1.01.1zsupported versions are z but input version is r#`)strider rr)Z kernel_sizer2r @ 0iir")r2r r rg?Zdownscale_in_infer)pmode)r r)rrversion num_classes with_poolrrrr_poolr!_conv1_conv2_conv3_conv4_conv5_conv6_conv7_conv8r_drop_conv9r _avg_pool)rr<r=r>Zsupported_versionsrrrrmsb    zSqueezeNet.__init__cCs@||}t|}||}|jdkrG||}||}||}||}||}| |}| |}| |}||}| |}n2||}||}||}||}||}||}| |}| |}| |}| |}|j dkr||}||}|jrt|}||}tj|ddgd}|S)Nr-rr1r#r&)rrrr?r<r@rArBrCrDrErFrGr=rHrIr>rJr'Zsqueeze)rr)rrrrrs@                             zSqueezeNet.forward)r,T)rrr__doc__rrr rrrrr+Ls 7r+cKs\t|fi|}|r,|tvsJ|dtt|dt|d}t|}|||S)NzJ model do not have a pretrained model now, you should set pretrained=Falserr")r+ model_urlsrr'loadZset_dict)archr< pretrainedkwargsmodelZ weight_pathparamrrr _squeezenets   rSFcKtdd|fi|S)aSqueezeNet v1.0 model from `"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size" `_. 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:`SqueezeNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of SqueezeNet v1.0 model. Examples: .. code-block:: python >>> import paddle >>> from paddle.vision.models import squeezenet1_0 >>> # build model >>> model = squeezenet1_0() >>> # build model and load imagenet pretrained weight >>> # model = squeezenet1_0(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) [1, 1000] r r-rSrOrPrrrr r cKrT)aSqueezeNet v1.1 model from `"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size" `_. 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:`SqueezeNet `. Returns: :ref:`api_paddle_nn_Layer`. An instance of SqueezeNet v1.1 model. Examples: .. code-block:: python >>> import paddle >>> from paddle.vision.models import squeezenet1_1 >>> # build model >>> model = squeezenet1_1() >>> # build model and load imagenet pretrained weight >>> # model = squeezenet1_1(pretrained=True) >>> x = paddle.rand([1, 3, 224, 224]) >>> out = model(x) >>> print(out.shape) [1, 1000] r r.rUrVrrrr rWr )F)r'Zpaddle.nn.functionalrZ functionalrZpaddle.base.param_attrrZ paddle.nnrrrrZpaddle.utils.downloadr__all__rLZLayerr r!r+rSr r rrrrs     } "