%`iGddlZddlmZddlZddlmZmZddlmZddlm Z ddl m Z ddl m Z dd lmZ dd ed ededeedeeefdeeefdeeefdeedefdZGddejZdS)N)Optional)nnTensor)init)_pair) Parameter)_assert_has_ops)_log_api_usage_oncer rrinputoffsetweightbiasstridepaddingdilationmaskreturnc4tjs2tjst t t |jd}|du} |.tj|jddf|j |j }|!tj||j |j }t|\} } t|\} } t|\}}|jdd\}}|j\}}}}|jdd|z|zz}||jdz}|dkr&td|jddd|z|ztj j|||||| | | | ||||| S) a? Performs Deformable Convolution v2, described in `Deformable ConvNets v2: More Deformable, Better Results `__ if :attr:`mask` is not ``None`` and Performs Deformable Convolution, described in `Deformable Convolutional Networks `__ if :attr:`mask` is ``None``. Args: input (Tensor[batch_size, in_channels, in_height, in_width]): input tensor offset (Tensor[batch_size, 2 * offset_groups * kernel_height * kernel_width, out_height, out_width]): offsets to be applied for each position in the convolution kernel. weight (Tensor[out_channels, in_channels // groups, kernel_height, kernel_width]): convolution weights, split into groups of size (in_channels // groups) bias (Tensor[out_channels]): optional bias of shape (out_channels,). Default: None stride (int or Tuple[int, int]): distance between convolution centers. Default: 1 padding (int or Tuple[int, int]): height/width of padding of zeroes around each image. Default: 0 dilation (int or Tuple[int, int]): the spacing between kernel elements. Default: 1 mask (Tensor[batch_size, offset_groups * kernel_height * kernel_width, out_height, out_width]): masks to be applied for each position in the convolution kernel. Default: None Returns: Tensor[batch_sz, out_channels, out_h, out_w]: result of convolution Examples:: >>> input = torch.rand(4, 3, 10, 10) >>> kh, kw = 3, 3 >>> weight = torch.rand(5, 3, kh, kw) >>> # offset and mask should have the same spatial size as the output >>> # of the convolution. In this case, for an input of 10, stride of 1 >>> # and kernel size of 3, without padding, the output size is 8 >>> offset = torch.rand(4, 2 * kh * kw, 8, 8) >>> mask = torch.rand(4, kh * kw, 8, 8) >>> out = deform_conv2d(input, offset, weight, mask=mask) >>> print(out.shape) >>> # returns >>> torch.Size([4, 5, 8, 8]) rNr )devicedtyper zthe shape of the offset tensor at dimension 1 is not valid. It should be a multiple of 2 * weight.size[2] * weight.size[3]. Got offset.shape[1]=z,, while 2 * weight.size[2] * weight.size[3]=)torchjit is_scripting is_tracingr deform_conv2dr shapezerosrrr RuntimeErrorops torchvision)rrrrrrrr out_channelsuse_maskstride_hstride_wpad_hpad_wdil_hdil_w weights_h weights_w_ n_in_channels n_offset_grps n_weight_grpss o/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/torchvision/ops/deform_conv.pyr r sb 9 ! ! # #+EI,@,@,B,B+M***<?L4H |{EKNA.u|5;WWW |{< EKPPPvHh>>LE5??LE5!<,Iy"[A}aLOI (ABM!V\!_4M |#)<? | |`adm`mpy`y | |   9 . .         ceZdZdZ ddedededed ed ed ed effd ZddZddedede edefdZ de fdZ xZ S) DeformConv2dz$ See :func:`deform_conv2d`. r rT in_channelsr& kernel_sizerrrgroupsrc tt|||zdkrtd||zdkrtd||_||_t ||_t ||_t ||_ t ||_ ||_ ttj|||z|jd|jd|_|r'ttj||_n|dd|dS)Nrz'in_channels must be divisible by groupsz(out_channels must be divisible by groupsr r)super__init__r ValueErrorr8r&rr9rrrr:rremptyrrregister_parameterreset_parameters) selfr8r&r9rrrr:r __class__s r4r=zDeformConv2d.__init__ssC D!!!  1 $ $FGG G & A % %GHH H&( --Fmm W~~ h   K kV&;T=Ma=PRVRbcdRe f f     2!%+l";";<rgs  ((((((((((((111111''''''"$% &!]] ] ] ] 6  ] #s(O ] 38_ ]CHo] 6 ] ]]]]@UUUUU29UUUUUr5