o Qeš%ã@sœddlZddlmZddlmZgZdddœZGdd„dejƒZdd d „Z gd ¢gd ¢gd ¢gd¢dœZ dd„Z ddd„Z ddd„Z ddd„Zddd„ZdS)éN)Úget_weights_path_from_url)z7https://paddle-hapi.bj.bcebos.com/models/vgg16.pdparamsZ 89bbffc0f87d260be9b8cdc169c991c4)z7https://paddle-hapi.bj.bcebos.com/models/vgg19.pdparamsZ 23b18bb13d8894f60f54e642be79a0dd)Úvgg16Úvgg19cs*eZdZdZd‡fdd„ Zdd„Z‡ZS) ÚVGGaVGG model from `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_. Args: features (nn.Layer): Vgg features create by function make_layers. 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 three fc layer or not. Default: True. Returns: :ref:`api_paddle_nn_Layer`. An instance of VGG model. Examples: .. code-block:: python import paddle from paddle.vision.models import VGG from paddle.vision.models.vgg import make_layers vgg11_cfg = [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'] features = make_layers(vgg11_cfg) vgg11 = VGG(features) x = paddle.rand([1, 3, 224, 224]) out = vgg11(x) print(out.shape) # [1, 1000] éèTc s€tt|ƒ ¡||_||_||_|rt d¡|_|dkr>t  t  dd¡t  ¡t  ¡t  dd¡t  ¡t  ¡t  d|¡¡|_ dSdS)N)érribi)ÚsuperrÚ__init__ÚfeaturesÚ num_classesÚ with_poolÚnnZAdaptiveAvgPool2DÚavgpoolÚ SequentialZLinearÚReLUZDropoutÚ classifier)Úselfr r r ©Ú __class__©úHD:\Projects\ConvertPro\env\Lib\site-packages\paddle/vision/models/vgg.pyr ?s"     ùÿz VGG.__init__cCs>| |¡}|jr | |¡}|jdkrt |d¡}| |¡}|S)Nré)r r rr ÚpaddleÚflattenr)rÚxrrrÚforwardSs     z VGG.forward)rT)Ú__name__Ú __module__Ú __qualname__Ú__doc__r rÚ __classcell__rrrrrs rFcCs~g}d}|D]3}|dkr|tjdddg7}qtj||ddd}|r/||t |¡t ¡g7}n||t ¡g7}|}qtj|ŽS)NéÚMé)Ú kernel_sizeZstrider)r$Úpadding)r Z MaxPool2DZConv2DZ BatchNorm2Drr)ÚcfgÚ batch_normZlayersZ in_channelsÚvZconv2drrrÚ make_layers`s r)) é@r"é€r"ér,r"ér-r"r-r-r")r*r*r"r+r+r"r,r,r"r-r-r"r-r-r")r*r*r"r+r+r"r,r,r,r"r-r-r-r"r-r-r-r")r*r*r"r+r+r"r,r,r,r,r"r-r-r-r-r"r-r-r-r-r")ÚAÚBÚDÚEcKshttt||dfi|¤Ž}|r2|tvsJd |¡ƒ‚tt|dt|dƒ}t |¡}| |¡|S)N)r'zL{} model do not have a pretrained model now, you should set pretrained=Falserr) rr)ÚcfgsÚ model_urlsÚformatrrÚloadÚ load_dict)Úarchr&r'Ú pretrainedÚkwargsÚmodelZ weight_pathÚparamrrrÚ_vggsÿ  ÿ  r<cKó&d}|r|d7}t|d||fi|¤ŽS)a VGG 11-layer model from `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. batch_norm (bool, optional): If True, returns a model with batch_norm layer. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`VGG `. Returns: :ref:`api_paddle_nn_Layer`. An instance of VGG 11-layer model. Examples: .. code-block:: python import paddle from paddle.vision.models import vgg11 # build model model = vgg11() # build vgg11 model with batch_norm model = vgg11(batch_norm=True) x = paddle.rand([1, 3, 224, 224]) out = model(x) print(out.shape) # [1, 1000] Úvgg11Ú_bnr.©r<©r8r'r9Z model_namerrrr>Žór>cKr=)aVGG 13-layer model from `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. batch_norm (bool): If True, returns a model with batch_norm layer. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`VGG `. Returns: :ref:`api_paddle_nn_Layer`. An instance of VGG 13-layer model. Examples: .. code-block:: python import paddle from paddle.vision.models import vgg13 # build model model = vgg13() # build vgg13 model with batch_norm model = vgg13(batch_norm=True) x = paddle.rand([1, 3, 224, 224]) out = model(x) print(out.shape) # [1, 1000] Úvgg13r?r/r@rArrrrC³rBrCcKr=)a VGG 16-layer model from `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. batch_norm (bool, optional): If True, returns a model with batch_norm layer. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`VGG `. Returns: :ref:`api_paddle_nn_Layer`. An instance of VGG 16-layer model. Examples: .. code-block:: python import paddle from paddle.vision.models import vgg16 # build model model = vgg16() # build vgg16 model with batch_norm model = vgg16(batch_norm=True) x = paddle.rand([1, 3, 224, 224]) out = model(x) print(out.shape) # [1, 1000] rr?r0r@rArrrrØrBrcKr=)a VGG 19-layer model from `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_. Args: pretrained (bool, optional): Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False. batch_norm (bool, optional): If True, returns a model with batch_norm layer. Default: False. **kwargs (optional): Additional keyword arguments. For details, please refer to :ref:`VGG `. Returns: :ref:`api_paddle_nn_Layer`. An instance of VGG 19-layer model. Examples: .. code-block:: python import paddle from paddle.vision.models import vgg19 # build model model = vgg19() # build vgg19 model with batch_norm model = vgg19(batch_norm=True) x = paddle.rand([1, 3, 224, 224]) out = model(x) print(out.shape) # [1, 1000] rr?r1r@rArrrrýrBr)F)FF)rZ paddle.nnr Zpaddle.utils.downloadrÚ__all__r3ZLayerrr)r2r<r>rCrrrrrrÚs&  ý Bø  % %%