+ jG^RIt^RIHt^RIt^RIHtHt^RIHt^RIH t ^RI H t ^RI H t ^RIHtR R R llt!R R ]P"4tR#)N)Optional)nnTensor)init)_pair) Parameter)_assert_has_ops)_log_api_usage_oncecV^8dQhR\R\R\R\\,R\\\3,R\\\3,R\\\3,R\\,R \/ #) inputoffsetweightbiasstridepaddingdilationmaskreturn)rrtupleint)formats"\/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torchvision/ops/deform_conv.py __annotate__rs]] ] ] ] 6  ] #s(O ] 38_ ]CHo] 6 ] ]c\PP4'g4\PP4'g\ \ 4\ 4VP^,pVRJp VfA\P!VP^,^3VPVPR7pVf-\P!WPVPR7p\V4wr\V4wr\V4wrVPRRwppVPwpppVP^,^V,V,,pVVP^,,pV^8Xd1\RVP^, R^V,V, 24h\PPP VVVVVV V V V VVVVV 4#)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]) N)devicedtypezthe 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 rrrrrrr out_channelsuse_maskstride_hstride_wpad_hpad_wdil_hdil_w weights_h weights_w_ n_in_channels n_offset_grps n_weight_grpss&&&&&&&& rr$r$sb 99 ! ! # #EII,@,@,B,BM*<<?L4H |{{EKKNA.u||5;;W |{{< EKKPvH>LE?LE!<<,Iy"[[A}aLLOI (ABM!V\\!_4M ##)<<?"33_`adm`mpy`y_z |  99 . .        rcaa]tRt^ntoRtR V3RlV3RllltV3RlRltR V3RlRlltV3RlR ltR t Vt V;t #) DeformConv2dz See :func:`deform_conv2d`. cJ<V^8dQhRS[RS[RS[RS[RS[RS[RS[RS[/#) r in_channelsr* kernel_sizerrrgroupsr)rbool)r __classdict__s"rrDeformConv2d.__annotate__ss[$ $ $ $  $  $  $ $ $ $ rc z<\S V`4\V4W,^8wd \R4hW',^8wd \R4hWnW n\ V4Vn\ V4Vn\ V4Vn \ V4Vn Wpn \\P!W!V,VP^,VP^,44VnV'd&\\P!V44VnMVP#RR4VP%4R#)rz'in_channels must be divisible by groupsz(out_channels must be divisible by groupsrN)super__init__r ValueErrorr;r*rr<rrrr=rr emptyrrregister_parameterreset_parameters) selfr;r*r<rrrr=r __class__s &&&&&&&&&rrCDeformConv2d.__init__ss D!  1 $FG G  A %GH H&( -Fm W~ h   KK V&;T=M=Ma=PRVRbRbcdRe f   !%++l";rws9  ((1']@U299Ur