TiSSKJr SSKJrJrJr SSKJr SSKJ r SSK J r J r J r JrJrJrJrJrJrJrJrJrJrJrJr SSKJrJr "SS\ 5rg ) ) annotations)OptionalSequenceTypeVar) get_schema)Opset1)BOOL COMPLEX64 COMPLEX128DOUBLEFLOATFLOAT16INT8INT16INT32INT64STRINGUINT8UINT16UINT32UINT64)OpOpsetc\rSrSrSr\"S\\\5r SS.SSjjr \"S\\\5r SSS S S .SS jjr \"S \\\5r S SS.SSjjr\"S\\\\\\\\\\\\\\\5rSS S.SSjjrSrg )Opset2(c2[R"USS5$)N)r__new__)clss a/var/www/html/ai-image-ml/venv/lib/python3.13/site-packages/onnxscript/onnx_opset/_impl/opset2.pyr Opset2.__new__)s}}S"a((T_GlobalLpPoolr)pcd[SSS5n[USU5nU"URX15SU06$)u[🌐 GlobalLpPool(2)](https://onnx.ai/onnx/operators/onnx__GlobalLpPool.html#globallppool-2 "Online Documentation") GlobalLpPool consumes an input tensor X and applies lp pool pooling across the values in the same channel. This is equivalent to LpPool with kernel size equal to the spatial dimension of input tensor. Args: X: (differentiable) Input data tensor from the previous operator; dimensions for image case are (N x C x H x W), where N is the batch size, C is the number of channels, and H and W are the height and the width of the data. For non image case, the dimensions are in the form of (N x C x D1 x D2 ... Dn), where N is the batch size. p: p value of the Lp norm used to pool over the input data. GlobalLpPoolrrr&rr_prepare_inputs)selfXr&schemaops r"r(Opset2.GlobalLpPool.s;$NAr2 nf -4''28a88r$T_LpPoolNOTSETN)auto_padr&padsstridesc l[SSS5n[USU5nU"URXq5UUUUUS.6$)u[🌐 LpPool(2)](https://onnx.ai/onnx/operators/onnx__LpPool.html#lppool-2 "Online Documentation") LpPool consumes an input tensor X and applies Lp pooling across the tensor according to kernel sizes, stride sizes, and pad lengths. Lp pooling consisting of computing the Lp norm on all values of a subset of the input tensor according to the kernel size and downsampling the data into the output tensor Y for further processing. Args: X: Input data tensor from the previous operator; dimensions for image case are (N x C x H x W), where N is the batch size, C is the number of channels, and H and W are the height and the width of the data. For non image case, the dimensions are in the form of (N x C x D1 x D2 ... Dn), where N is the batch size. auto_pad: auto_pad must be either NOTSET, SAME_UPPER, SAME_LOWER or VALID. Where default value is NOTSET, which means explicit padding is used. SAME_UPPER or SAME_LOWER mean pad the input so that the output spatial size match the input.In case of odd number add the extra padding at the end for SAME_UPPER and at the beginning for SAME_LOWER. VALID mean no padding. kernel_shape: The size of the kernel along each axis. p: p value of the Lp norm used to pool over the input data. pads: Padding for the beginning and ending along each spatial axis, it can take any value greater than or equal to 0. The value represent the number of pixels added to the beginning and end part of the corresponding axis. `pads` format should be as follow [x1_begin, x2_begin...x1_end, x2_end,...], where xi_begin the number of pixels added at the beginning of axis `i` and xi_end, the number of pixels added at the end of axis `i`. This attribute cannot be used simultaneously with auto_pad attribute. If not present, the padding defaults to 0 along start and end of each spatial axis. strides: Stride along each spatial axis. LpPoolrr)r2 kernel_shaper&r3r4r)) r+r,r2r7r&r3r4r-r.s r"r6 Opset2.LpPoolFsKdHa, h '  ! !& ,%   r$T_Padconstantg)modevaluecf[SSS5n[USU5nU"URXQ5X#US.6$)u[🌐 Pad(2)](https://onnx.ai/onnx/operators/onnx__Pad.html#pad-2 "Online Documentation") Given `data` tensor, pads, mode, and value. Example: Insert 0 pads to the beginning of the second dimension. data = [ [1.0, 1.2], [2.3, 3.4], [4.5, 5.7], ] pads = [0, 2, 0, 0] output = [ [ [0.0, 0.0, 1.0, 1.2], [0.0, 0.0, 2.3, 3.4], [0.0, 0.0, 4.5, 5.7], ], ] Args: data: Input tensor. mode: Three modes: constant(default), reflect, edge pads: List of integers indicating the number of padding elements to add or remove (if negative) at the beginning and end of each axis. For 2D it is the number of pixels. `pads` rank should be double of the input's rank. `pads` format should be as follow [x1_begin, x2_begin...x1_end, x2_end,...], where xi_begin the number of pixels added at the beginning of axis `i` and xi_end, the number of pixels added at the end of axis `i`. value: One float, indicates the value to be filled. Padrr)r;r3r<r))r+datar;r3r<r-r.s r"r> Opset2.Pads<ZE1b) eV $4''5DSXYYr$T_Splitraxissplitcd[SSS5n[USU5nU"URXA5X#S.6$)u[🌐 Split(2)](https://onnx.ai/onnx/operators/onnx__Split.html#split-2 "Online Documentation") Split a tensor into a list of tensors, along the specified 'axis'. Lengths of the parts can be specified using argument 'split'. Otherwise, the tensor is split to equal sized parts. Args: input: The tensor to split axis: Which axis to split on. split: length of each output SplitrrrBr))r+inputrCrDr-r.s r"rF Opset2.Splits8$GQ+ gv &4''6TOOr$)r,r%r&intreturnr%)r,r0r2strr7 Sequence[int]r&rJr3Optional[Sequence[int]]r4rNrKr0) r?r9r;rLr3rMr<floatrKr9)rGrArCrJrDrNrKrA)__name__ __module__ __qualname____firstlineno__r rr r rr%r(r0r6r9r>r r r rrrrrrrrrrArF__static_attributes__rIr$r"rr(sV)-vugFN:;9,z65':H !(,+/; ;  ; $ ;  ; &; );  ; z GVUG 4E  /Z/Z /Z  /Z  /Z /Zb       !G(./QUPP'*P7NP PPr$rN) __future__rtypingrrr onnx.defsr"onnxscript.onnx_opset._impl.opset1ronnxscript.onnx_typesr r r r r rrrrrrrrrronnxscript.valuesrrrrIr$r"r[sD#.. 5"(uPVuPr$