o )i@sddlZddlZddlmmZddlmZmZddlmZ dded e d e d e d e d e defddZ dded e d e d e d e d e defddZ ejdGdddejZejdGdddeZdS)N)nnTensor)_log_api_usage_onceFư>Tinputp block_sizeinplaceepstrainingreturnc Cs^tjstjstt|dks|dkrtd|d|jdkr,td|jd|r2|dkr4|S|\}}}} t || |}||| |d||d | |d } tj ||||d | |d f|j |j d } | | tj| |dgdd d } tj| d ||f|dd} d | } | || } |r|| | |S|| | }|S)a Implements DropBlock2d from `"DropBlock: A regularization method for convolutional networks" `. Args: input (Tensor[N, C, H, W]): The input tensor or 4-dimensions with the first one being its batch i.e. a batch with ``N`` rows. p (float): Probability of an element to be dropped. block_size (int): Size of the block to drop. inplace (bool): If set to ``True``, will do this operation in-place. Default: ``False``. eps (float): A value added to the denominator for numerical stability. Default: 1e-6. training (bool): apply dropblock if is ``True``. Default: ``True``. Returns: Tensor[N, C, H, W]: The randomly zeroed tensor after dropblock. ?4drop probability has to be between 0 and 1, but got .z#input should be 4 dimensional. Got dimensions.rdtypedevicervalue)rrZstrideZ kernel_sizepadding)torchjit is_scripting is_tracingr drop_block2d ValueErrorndimsizeminemptyrr bernoulli_FpadZ max_pool2dnumelsummul_) rrr r r r NCHWgammanoisenormalize_scaler3i/var/www/html/eduruby.in/lip-sync/lip-sync-env/lib/python3.10/site-packages/torchvision/ops/drop_block.pyr s,   ,,  r cCs~tjstjstt|dks|dkrtd|d|jdkr,td|jd|r2|dkr4|S|\}}}} } t ||| | }||| | |d||d | |d | |d } tj ||||d | |d | |d f|j |j d } | | tj| |d gd d d} tj| d|||f|d d} d | } | || } |r|| | |S|| | }|S)a  Implements DropBlock3d from `"DropBlock: A regularization method for convolutional networks" `. Args: input (Tensor[N, C, D, H, W]): The input tensor or 5-dimensions with the first one being its batch i.e. a batch with ``N`` rows. p (float): Probability of an element to be dropped. block_size (int): Size of the block to drop. inplace (bool): If set to ``True``, will do this operation in-place. Default: ``False``. eps (float): A value added to the denominator for numerical stability. Default: 1e-6. training (bool): apply dropblock if is ``True``. Default: ``True``. Returns: Tensor[N, C, D, H, W]: The randomly zeroed tensor after dropblock. rrrrz#input should be 5 dimensional. Got rrrrrr)rrrr)rrrrr drop_block3dr!r"r#r$r%rrr&r'r(Z max_pool3dr)r*r+)rrr r r r r,r-Dr.r/r0r1r2r3r3r4r87s4  <,  r8c sXeZdZdZddededededd f fd d Zd edefd dZ de fddZ Z S) DropBlock2dz# See :func:`drop_block2d`. Frrr r r r Ncs&t||_||_||_||_dSN)super__init__rr r r selfrr r r  __class__r3r4r=qs  zDropBlock2d.__init__rcCt||j|j|j|j|jSz Args: input (Tensor): Input feature map on which some areas will be randomly dropped. Returns: Tensor: The tensor after DropBlock layer. )r rr r r r r?rr3r3r4forwardyzDropBlock2d.forwardcCs*|jjd|jd|jd|jd}|S)Nz(p=z , block_size=z , inplace=))rA__name__rr r )r?sr3r3r4__repr__s&zDropBlock2d.__repr__Fr) rH __module__ __qualname____doc__floatintboolr=rrEstrrJ __classcell__r3r3r@r4r:ls $ r:c sJeZdZdZddededededd f fd d Zd edefd dZ Z S) DropBlock3dz# See :func:`drop_block3d`. Frrr r r r Ncst||||dSr;)r<r=r>r@r3r4r=szDropBlock3d.__init__rcCrBrC)r8rr r r r rDr3r3r4rErFzDropBlock3d.forwardrK) rHrLrMrNrOrPrQr=rrErSr3r3r@r4rTs$rT)FrT)rZtorch.fxZtorch.nn.functionalrZ functionalr'rutilsrrOrPrQr r8ZfxwrapModuler:rTr3r3r3r4sR  / 2