U h5@sddlZddlmZmZmZmZmZmZddlZddlm Z ddl m Z m Z ej jjZGdddej jZGdd d ej jZGd d d eZGd d d eZGdddej jZGdddej jZGdddej jZdS)N)CallableListOptionalSequenceTupleUnion)Tensor)_log_api_usage_once _make_ntuplecsreZdZdZdeedfdd 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__r rZregister_buffertorchZonesZzeros)selfrr __class__F/var/www/html/venv/lib/python3.8/site-packages/torchvision/ops/misc.pyrs zFrozenBatchNorm2d.__init__) state_dictprefixlocal_metadatastrict missing_keysunexpected_keys error_msgsc s2|d}||kr||=t|||||||dS)NZnum_batches_tracked)r_load_from_state_dict) rrrrrr r!r"Znum_batches_tracked_keyrrrr##s z'FrozenBatchNorm2d._load_from_state_dictxreturncCsr|jdddd}|jdddd}|jdddd}|jdddd}|||j}|||}|||S)N)rZreshaperrrrZrsqrt)rr%wbrvZrmscalerrrrforward5s zFrozenBatchNorm2d.forward)r&cCs$|jjd|jjdd|jdS)N(rz, eps=))r__name__rshaper)rrrr__repr__@szFrozenBatchNorm2d.__repr__)r )r0 __module__ __qualname____doc__intfloatrdictstrboolrr#rr-r2 __classcell__rrrrr s   r cseZdZddddejjejjdddejjf eee ee edffe ee edffe e ee edfe fee e dejjfe e dejjfe ee edffe ee ee dejjfdd fdd ZZS) ConvNormActivationr'NT.) in_channels out_channels kernel_sizestridepaddinggroups norm_layeractivation_layerdilationinplacer conv_layerr&c  s|dkrxttr.ttr.dd}nJttr@tnt} t| t| tfddt| D}| dkr|dk} | |||||| dg}|dk r||||dk r| dkrind| i}||f|tj |t |||_ |j t krtddS)Nr'r c3s&|]}|dd|VqdS)r'r Nr).0irFr@rr \sz.ConvNormActivation.__init__..)rFrCrrGzhDon't use ConvNormActivation directly, please use Conv2dNormActivation and Conv3dNormActivation instead.) isinstancer6rlenr tuplerangeappendrrr r?rr<warningswarn)rr>r?r@rArBrCrDrErFrGrrHZ _conv_dimlayersparamsrrKrrEs@     zConvNormActivation.__init__)r0r3r4rnn BatchNorm2dReLUConv2dr6rrrr9rModuler:rr;rrrrr<Ds2r<cseZdZdZddddejjejjdddf eee ee eeffe ee eeffe e ee eefe fee e dejjfe e dejjfe ee eeffe ee edd fdd ZZS) 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 be 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 won't 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 won't 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``. r=r'NT. r>r?r@rArBrCrDrErFrGrr&c s*t||||||||| | | tjj dSN)rrrrVrY rr>r?r@rArBrCrDrErFrGrrrrrszConv2dNormActivation.__init__)r0r3r4r5rrVrWrXr6rrrr9rrZr:rr;rrrrr[}s0r[cseZdZdZddddejjejjdddf eee ee eeeffe ee eeeffe e ee eeefe fee e dejjfe e dejjfe ee eeeffe ee edd fdd ZZS) 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 be 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 won't 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 won't 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``. r=r'NT.r\c s*t||||||||| | | tjj dSr])rrrrVZConv3dr^rrrrszConv3dNormActivation.__init__)r0r3r4r5rrVZ BatchNorm3drXr6rrrr9rrZr: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') rrr rrVZAdaptiveAvgPool2davgpoolrYfc1fc2rcrd)rrarbrcrdrrrrs zSqueezeExcitation.__init__)inputr&cCs2||}||}||}||}||Sr])rerfrcrgrdrrhr,rrr_scales     zSqueezeExcitation._scalecCs||}||Sr])rjrirrrr-s zSqueezeExcitation.forward)r0r3r4r5rrVrXZSigmoidr6rrZrrrjr-r;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 linear layer. If ``None`` this layer won't 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 linear layer. If ``None`` this layer won't be used. Default: ``torch.nn.ReLU`` inplace (bool, optional): Parameter for the activation layer, which can optionally do the operation in-place. Default is ``None``, which uses the respective default values of the ``activation_layer`` and Dropout layer. bias (bool): Whether to use bias in the linear layer. Default ``True`` dropout (float): The probability for the dropout layer. Default: 0.0 NTg.)r>hidden_channelsrDrErGrdropoutc s|dkr ind|i}g} |} |ddD]\} | tjj| | |d|dk rZ| || | |f|| tjj|f|| } q(| tjj| |d|d| tjj|f|tj| t|dS)NrGr()r)rQrrVZLinearZDropoutrrr ) rr>rlrDrErGrrmrUrTZin_dimZ hidden_dimrrrrs  z MLP.__init__)r0r3r4r5rrVrXr6rrrrZr:r7rr;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||_dSr])rrro)rrorrrr;s zPermute.__init__r$cCst||jSr])rZpermutero)rr%rrrr-?szPermute.forward) r0r3r4r5rr6rrr-r;rrrrrn4srn)rRtypingrrrrrrrrutilsr r rVZ functionalZ interpolaterZr Z Sequentialr<r[r_r`rkrnrrrrs   7921'-