EiGSSKrSSKJr SSKrSSKJrJr SSKJr SSKJ r SSK J r SSK J r SS KJr SS \S \S \S \\S\\\4S\\\4S\\\4S\\S\4Sjjr"SS\R&5rg)N)Optional)nnTensor)init)_pair) Parameter)_assert_has_ops)_log_api_usage_onceinputoffsetweightbiasstridepaddingdilationmaskreturnc^[RR5(d2[RR5(d[ [ 5 [ 5 URSnUSLn Uc9[R"URSS4URURS9nUc)[R"XRURS9n[U5up[U5up[U5upURSSunnURunn nURSSU-U--nUURS-nUS:Xa$[SURSSSU-U-35e[RRR UUUUUU U U U UUUUU 5$) 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]) rN)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)r r rrrrrr out_channelsuse_maskstride_hstride_wpad_hpad_wdil_hdil_w weights_h weights_w_ n_in_channels n_offset_grps n_weight_grpss X/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torchvision/ops/deform_conv.pyrrsb 99 ! ! # #EII,@,@,B,BM*<<?L4H |{{EKKNA.u||5;;W |{{< EKKPvH>LE?LE!<<,Iy"[[A}aLLOI (ABM!V\\!_4M ##)<<?"33_`adm`mpy`y_z |  99 . .        c^\rSrSrSrSS\S\S\S\S\S\S \S \4U4S jjjrSS jrSS\ S\ S\ \ S \ 4Sjjr S \ 4Sjr SrU=r$) DeformConv2dnz See :func:`deform_conv2d`. in_channelsr$ kernel_sizerrrgroupsrc J>[T U]5 [U5 X-S:wa [S5eX'-S:wa [S5eXlX l[ U5Ul[ U5Ul[ U5Ul [ U5Ul Xpl [[R"X!U-URSURS55UlU(a%[[R"U55UlOUR#SS5 UR%5 g)Nrz'in_channels must be divisible by groupsz(out_channels must be divisible by groupsrr)super__init__r ValueErrorr7r$rr8rrrr9rremptyrrregister_parameterreset_parameters) selfr7r$r8rrrr9r __class__s r2r<DeformConv2d.__init__ss D!  1 $FG G  A %GH H&( -Fm W~ h   KK V&;T=M=Ma=PRVRbRbcdRe f   !%++l";rns  ((1'"$% &!] ] ] ] 6  ] #s(O ] 38_ ]CHo] 6 ] ]@U299Ur3