a PSicw1@sddlZddlmZmZmZddlZddlmZddlmZej j j Z Gdddej j Z Gdd d ej jZGd d d eZGd d d eZGdddej j ZGdddej jZGdddej j ZdS)N)CallableListOptional)Tensor)_log_api_usage_oncecsreZdZdZdeedfdd Zeeee e ee ee edfdd Z e e d d d Z ed d dZZS)FrozenBatchNorm2da! BatchNorm2d where the batch statistics and the affine parameters are fixed Args: num_features (int): Number of features ``C`` from an expected input of size ``(N, C, H, W)`` eps (float): a value added to the denominator for numerical stability. Default: 1e-5 h㈵>) num_featuresepscsdtt|||_|dt||dt||dt||dt|dS)Nweightbias running_mean running_var)super__init__rr register_buffertorchoneszeros)selfr r  __class__P/var/www/html/django/DPS/env/lib/python3.9/site-packages/torchvision/ops/misc.pyrs zFrozenBatchNorm2d.__init__) state_dictprefixlocal_metadatastrict missing_keysunexpected_keys error_msgsc s2|d}||vr||=t|||||||dS)Nnum_batches_tracked)r_load_from_state_dict) rrrrrrr r!num_batches_tracked_keyrrrr##s z'FrozenBatchNorm2d._load_from_state_dictxreturncCsr|jdddd}|jdddd}|jdddd}|jdddd}|||j}|||}|||S)N)r reshaper rrr rsqrt)rr&wbrvrmscaler rrrforward5s zFrozenBatchNorm2d.forward)r'cCs$|jjd|jjdd|jdS)N(rz, eps=))r__name__r shaper )rrrr__repr__@szFrozenBatchNorm2d.__repr__)r )r4 __module__ __qualname____doc__intfloatrdictstrboolrr#rr1r6 __classcell__rrrrr s   rcseZdZddddejjejjdddejjf eeeee eee e dejj fe e dejj fee e e e e dejj fdd fdd Z ZS) ConvNormActivationr(NT.) in_channels out_channels kernel_sizestridepaddinggroups norm_layeractivation_layerdilationinplacer conv_layerr'c  s|dur|dd| }| dur(|du} | |||||| || dg} |durX| |||dur| durlind| i}| |fi|tj| t|||_|jtkrtddS)Nr(r)rJrGr rKzhDon't use ConvNormActivation directly, please use Conv2dNormActivation and Conv3dNormActivation instead.) appendrrrrCrr@warningswarn)rrBrCrDrErFrGrHrIrJrKr rLlayersparamsrrrrEs6   zConvNormActivation.__init__)r4r7r8rnn BatchNorm2dReLUConv2dr:rrModuler>rr?rrrrr@Ds2r@cseZdZdZddddejjejjdddf eeeee eee e dejj fe e dejj fee e e e dd fdd Z ZS) Conv2dNormActivationa Configurable block used for Convolution2d-Normalization-Activation blocks. Args: in_channels (int): Number of channels in the input image out_channels (int): Number of channels produced by the Convolution-Normalization-Activation block kernel_size: (int, optional): Size of the convolving kernel. Default: 3 stride (int, optional): Stride of the convolution. Default: 1 padding (int, tuple or str, optional): Padding added to all four sides of the input. Default: None, in which case it will calculated as ``padding = (kernel_size - 1) // 2 * dilation`` groups (int, optional): Number of blocked connections from input channels to output channels. Default: 1 norm_layer (Callable[..., torch.nn.Module], optional): Norm layer that will be stacked on top of the convolution layer. If ``None`` this layer wont be used. Default: ``torch.nn.BatchNorm2d`` activation_layer (Callable[..., torch.nn.Module], optional): Activation function which will be stacked on top of the normalization layer (if not None), otherwise on top of the conv layer. If ``None`` this layer wont be used. Default: ``torch.nn.ReLU`` dilation (int): Spacing between kernel elements. Default: 1 inplace (bool): Parameter for the activation layer, which can optionally do the operation in-place. Default ``True`` bias (bool, optional): Whether to use bias in the convolution layer. By default, biases are included if ``norm_layer is None``. rAr(NT. rBrCrDrErFrGrHrIrJrKr r'c s*t||||||||| | | tjj dSN)rrrrRrU rrBrCrDrErFrGrHrIrJrKr rrrrszConv2dNormActivation.__init__)r4r7r8r9rrRrSrTr:rrrVr>rr?rrrrrWws0rWcseZdZdZddddejjejjdddf eeeee eee e dejj fe e dejj fee e e e dd fdd Z ZS) Conv3dNormActivationa Configurable block used for Convolution3d-Normalization-Activation blocks. Args: in_channels (int): Number of channels in the input video. out_channels (int): Number of channels produced by the Convolution-Normalization-Activation block kernel_size: (int, optional): Size of the convolving kernel. Default: 3 stride (int, optional): Stride of the convolution. Default: 1 padding (int, tuple or str, optional): Padding added to all four sides of the input. Default: None, in which case it will calculated as ``padding = (kernel_size - 1) // 2 * dilation`` groups (int, optional): Number of blocked connections from input channels to output channels. Default: 1 norm_layer (Callable[..., torch.nn.Module], optional): Norm layer that will be stacked on top of the convolution layer. If ``None`` this layer wont be used. Default: ``torch.nn.BatchNorm3d`` activation_layer (Callable[..., torch.nn.Module], optional): Activation function which will be stacked on top of the normalization layer (if not None), otherwise on top of the conv layer. If ``None`` this layer wont be used. Default: ``torch.nn.ReLU`` dilation (int): Spacing between kernel elements. Default: 1 inplace (bool): Parameter for the activation layer, which can optionally do the operation in-place. Default ``True`` bias (bool, optional): Whether to use bias in the convolution layer. By default, biases are included if ``norm_layer is None``. rAr(NT.rXc s*t||||||||| | | tjj dSrY)rrrrRConv3drZrrrrszConv3dNormActivation.__init__)r4r7r8r9rrR BatchNorm3drTr:rrrVr>rr?rrrrr[s0r[csteZdZdZejjejjfeee dejj fe dejj fddfdd Z e e ddd Z e e dd d ZZS) SqueezeExcitationaE This block implements the Squeeze-and-Excitation block from https://arxiv.org/abs/1709.01507 (see Fig. 1). Parameters ``activation``, and ``scale_activation`` correspond to ``delta`` and ``sigma`` in eq. 3. Args: input_channels (int): Number of channels in the input image squeeze_channels (int): Number of squeeze channels activation (Callable[..., torch.nn.Module], optional): ``delta`` activation. Default: ``torch.nn.ReLU`` scale_activation (Callable[..., torch.nn.Module]): ``sigma`` activation. Default: ``torch.nn.Sigmoid`` .N)input_channelssqueeze_channels activationscale_activationr'csXtt|tjd|_tj||d|_tj||d|_ ||_ ||_ dS)Nr() rrrrrRAdaptiveAvgPool2davgpoolrUfc1fc2rarb)rr_r`rarbrrrrs zSqueezeExcitation.__init__)inputr'cCs2||}||}||}||}||SrY)rdrerarfrbrrgr0rrr_scales     zSqueezeExcitation._scalecCs||}||SrY)rirhrrrr1s zSqueezeExcitation.forward)r4r7r8r9rrRrTSigmoidr:rrVrrrir1r?rrrrr^sr^c sjeZdZdZdejjdddfeeee e dejj fe e dejj fe e e e dfdd ZZS) MLPaThis block implements the multi-layer perceptron (MLP) module. Args: in_channels (int): Number of channels of the input hidden_channels (List[int]): List of the hidden channel dimensions norm_layer (Callable[..., torch.nn.Module], optional): Norm layer that will be stacked on top of the convolution layer. If ``None`` this layer wont be used. Default: ``None`` activation_layer (Callable[..., torch.nn.Module], optional): Activation function which will be stacked on top of the normalization layer (if not None), otherwise on top of the conv layer. If ``None`` this layer wont be used. Default: ``torch.nn.ReLU`` inplace (bool): Parameter for the activation layer, which can optionally do the operation in-place. Default ``True`` bias (bool): Whether to use bias in the linear layer. Default ``True`` dropout (float): The probability for the dropout layer. Default: 0.0 NTg.)rBhidden_channelsrHrIrKr dropoutc s|dur ind|i}g} |} |ddD]d} | tjj| | |d|durZ| || | |fi|| tjj|fi|| } q(| tjj| |d|d| tjj|fi|tj| t|dS)NrKr))r )rMrrRLinearDropoutrrr) rrBrlrHrIrKr rmrQrPin_dim hidden_dimrrrrs  z MLP.__init__)r4r7r8r9rrRrTr:rrrrVr>r;rr?rrrrrksrkcs:eZdZdZeedfdd ZeedddZZ S)PermutezThis module returns a view of the tensor input with its dimensions permuted. Args: dims (List[int]): The desired ordering of dimensions )dimscst||_dSrY)rrrs)rrsrrrr4s zPermute.__init__r%cCst||jSrY)rpermuters)rr&rrrr18szPermute.forward) r4r7r8r9rr:rrr1r?rrrrrr-srr)rNtypingrrrrrutilsrrR functional interpolaterVr Sequentialr@rWr[r^rkrrrrrrs   7321',